diff --git a/LDP/howto/linuxdoc/AI-Alife-HOWTO.sgml b/LDP/howto/linuxdoc/AI-Alife-HOWTO.sgml index ad61bdf8..fc9a2e58 100644 --- a/LDP/howto/linuxdoc/AI-Alife-HOWTO.sgml +++ b/LDP/howto/linuxdoc/AI-Alife-HOWTO.sgml @@ -4,17 +4,15 @@ GNU/Linux AI & Alife HOWTO <author>by <htmlurl url="mailto:jae@zhar.net" name="John Eikenberry"> -<date>v2.4, 12 Jun 2008 +<date>v3.0, 15 Dec 2012 <abstract> This howto mainly contains information about, and links to, -various AI related software libraries, applications, etc. -that work on the GNU/Linux platform. All of it is (at least) -free for personal use. +various AI related software libraries, applications, etc. +that work on the GNU/Linux platform. All of it is (at least) +free for personal use. -The new master page for this document is -<htmlurl url="http://zhar.net/howto/" - name="http://zhar.net/howto/"> +The new master page for this document is <htmlurl url="http://zhar.net/howto/"> </abstract> <toc> @@ -39,7 +37,7 @@ including artificial intelligence and artificial life. The purpose of this Howto is to provide a source to find out about various software packages, code libraries, and anything else that will help someone get started working with (and find resources -for) artificial intelligence, artificial life, etc. All done with +for) artificial intelligence, artificial life, etc. All done with GNU/Linux specifically in mind. <sect1>What's New @@ -47,7 +45,7 @@ GNU/Linux specifically in mind. <itemize> - <item>v3.0 (In progress) - + <item>v3.0 - <p>New entries: <ref id="ORTS">, <ref id="FANN">, <ref id="OpenCV">, <ref id="CBR Microprograms">, <ref id="ConceptNet">, <ref id="FreeHAL">, @@ -55,7 +53,7 @@ GNU/Linux specifically in mind. <ref id="PyIE">, <ref id="Pyevolve">, <ref id="txevolver">, <ref id="python-dlp">, <ref id="CompLearn">, <ref id="dbacl">, <ref id="Maximum Entropy Toolkit">, <ref id="pebl">, <ref id="FLiP">, - <ref id="Carmen">, <ref id="Orca">, <ref id="ROS">, <ref id="YARP">, + <ref id="Carmen">, <ref id="Orca">, <ref id="ROS">, <ref id="YARP">, <ref id="Neuroph">, <ref id="MLAP book samples">, <ref id="Elefant">, <ref id="Evocosm">, <ref id="Critterding">, <ref id="MRPT">, <ref id="PyBrain">, <ref id="peach">, <ref id="brain">, <ref id="FREVO">, @@ -63,27 +61,30 @@ GNU/Linux specifically in mind. <ref id="EAP">, <ref id="GenePool">, <ref id="Milk">, <ref id="OpenCog">, <ref id="Pattern">, <ref id="CognitiveFoundry">, <ref id="clasp">, <ref id="timbl">, <ref id="MBT">, <ref id="scikits.learn">, - <ref id="Biogenesis"> and <ref id="brain-simulator">. + <ref id="NeuroLab">, <ref id="Biogenesis">, <ref id="brain-simulator">. + <ref id="Torch5">, <ref id="Encog">, <ref id="Nengo">, + <ref id="DEAP"> and <ref id="Emergent">. - <p>Changed the name of the "Traditional" section to - <ref id="Symbolic Systems (GOFAI)">. Added new section, + <p>Changed the name of the "Traditional" section to + <ref id="Symbolic Systems (GOFAI)">. Added new section, <ref id="Statistical & Machine Learning">. <p>Seems someone has resuscitated <ref id="EMA-XPS">. Not very active, but enough to pull out of the dead projects area and place back amounst the - living. Also Fixed a few links. + living. I also fixed many links and moved quite a few dead projects to + <ref id="Missing & Dead">. <item>v2.4 - <p>New entries: <ref id="Eprover">, <ref id="Player">, <ref id="Logfun">, - <ref id="Livingstone2">, <ref id="Quackle">, <ref id="LingPipe">, - <ref id="GATE">, <ref id="Infon Battle Arena">, <ref id="CLARAty">, + <ref id="Livingstone2">, <ref id="Quackle">, <ref id="LingPipe">, + <ref id="GATE">, <ref id="Infon Battle Arena">, <ref id="CLARAty">, <ref id="Reverend">, <ref id="Shogun">, <ref id="Nanopond">, <ref id="Polyworld">, <ref id="Fluidiom">, <ref id="NEAT">, <ref id="Framsticks">, <ref id="URBI">, <ref id="RobotFlow">, <ref id="Nero">, <ref id="ffnet">, <ref id="Alloy">, - <ref id="Pyke">, <ref id="NuPIC">, <ref id="Simbad">, <ref id="Robodeb">, + <ref id="Pyke">, <ref id="NuPIC">, <ref id="Simbad">, <ref id="Robodeb">, <ref id="Loom">, <ref id="PowerLoom">, <ref id="tinygp">, <ref id="Curry">, <ref id="JGAP">, <ref id="PyCLIPS">, and <ref id="STELLA">. @@ -101,11 +102,11 @@ GNU/Linux specifically in mind. <p>New entries: <ref id="Yampa">, <ref id="pygene">, <ref id="Push">, <ref id="ANNEvolve">, <ref id="dgpf">, <ref id="Golly">, <ref id="IBAL">, <ref id="3APL">, <ref id="OSCAR">, - and <ref id="RobocodeNG">. + and <ref id="RobocodeNG">. - <p>Updated information for some entries including <ref id="Yale">, + <p>Updated information for some entries including <ref id="Yale">, <ref id="Joone">, <ref id="Drone">, <ref id="Biome">, <ref id="ECLiPSe">, - <ref id="Xtoys">, <ref id="GECO">, + <ref id="Xtoys">, <ref id="GECO">, <ref id="Creatures Docking Station"> and others. <p>I also changed the MIA section to <ref id="Missing & Dead"> which now @@ -164,7 +165,7 @@ GNU/Linux specifically in mind. <item>v1.3 - Putting a dent in the backlog, I added 30+ new entries today and submitted it to the LDP. <item>Previous records were in a mixed format with site updates. See the - <htmlurl url="http://zhar.net/howto/oldnotes/" name="old notes"> + <htmlurl url="http://zhar.net/howto/oldnotes/" name="old notes"> section of the master site for them. </itemize> @@ -174,18 +175,18 @@ GNU/Linux specifically in mind. All this software should be available via the net (ftp || http). The links to where to find it will be provided in the description of each package. There will also be plenty of software not covered on these -pages (which is usually platform independent) located on one of the -resources listed on the <htmlurl url="http://zhar.net/attic/mlp/ai/" +pages (which is usually platform independent) located on one of the +resources listed on the <htmlurl url="http://zhar.net/howto/ai_links/" name="links section"> of the Master Site (given above). - + <sect1>Updates and comments -<p> +<p> If you find any mistakes, know of updates to one of the items below, or have problems compiling any of the applications, please mail me at: -<htmlurl url="mailto:jae@zhar.net" name="jae@zhar.net"> -and I'll see what I can do. +<htmlurl url="mailto:jae@zhar.net" name="jae@zhar.net"> +and I'll see what I can do. If you know of any AI/Alife applications, class libraries, @@ -194,9 +195,9 @@ about them. Include your name, ftp and/or http sites where they can be found, plus a brief overview/commentary on the software (this info would make things a lot easier on me... but don't feel obligated ;). - + I know that keeping this list up to date and expanding it will take quite -a bit of work. So please be patient (I do have other projects). I hope you +a bit of work. So please be patient (I do have other projects). I hope you will find this document helpful. <sect1>Copyright/License @@ -205,53 +206,52 @@ Copyright (c) 1996-2009 John A. Eikenberry LICENSE - This document may be reproduced and distributed in whole or in part, in - any medium physical or electronic, provided that this license notice is - displayed in the reproduction. Commercial redistribution is permitted and - encouraged. Thirty days advance notice, via email to the author, of - redistribution is appreciated, to give the authors time to provide updated + This document may be reproduced and distributed in whole or in part, in + any medium physical or electronic, provided that this license notice is + displayed in the reproduction. Commercial redistribution is permitted and + encouraged. Thirty days advance notice, via email to the author, of + redistribution is appreciated, to give the authors time to provide updated documents. A. REQUIREMENTS OF MODIFIED WORKS - All modified documents, including translations, anthologies, and partial - documents, must meet the following requirements: + All modified documents, including translations, anthologies, and partial + documents, must meet the following requirements: <p><itemize> <item>The modified version must be labeled as such. <item>The person making the modifications must be identified. <item>Acknowledgement of the original author must be retained. <item>The location of the original unmodified document be identified. - <item>The original author's name(s) may not be used to assert or imply - endorsement of the resulting document without the original author's + <item>The original author's name(s) may not be used to assert or imply + endorsement of the resulting document without the original author's permission. </itemize> - In addition it is requested (not required) that: + In addition it is requested (not required) that: <itemize> - <item>The modifications (including deletions) be noted. - <item>The author be notified by email of the modification in advance of - redistribution, if an email address is provided in the document. + <item>The modifications (including deletions) be noted. + <item>The author be notified by email of the modification in advance of + redistribution, if an email address is provided in the document. </itemize> - As a special exception, anthologies of LDP documents may include a single - copy of these license terms in a conspicuous location within the anthology - and replace other copies of this license with a reference to the single - copy of the license without the document being considered "modified" for - the purposes of this section. + As a special exception, anthologies of LDP documents may include a single + copy of these license terms in a conspicuous location within the anthology + and replace other copies of this license with a reference to the single + copy of the license without the document being considered "modified" for + the purposes of this section. - Mere aggregation of LDP documents with other documents or programs on the - same media shall not cause this license to apply to those other works. + Mere aggregation of LDP documents with other documents or programs on the + same media shall not cause this license to apply to those other works. - All translations, derivative documents, or modified documents that - incorporate this document may not have more restrictive license terms - than these, except that you may require distributors to make the resulting - document available in source format. + All translations, derivative documents, or modified documents that + incorporate this document may not have more restrictive license terms + than these, except that you may require distributors to make the resulting + document available in source format. - - <sect>Symbolic Systems (GOFAI) + <label id="Symbolic Systems (GOFAI)"> <p> @@ -264,21 +264,21 @@ LICENSE been used for such things as medical diagnosis support and credit checking systems. - + <sect1>AI class/code libraries <p> These are libraries of code or classes for use in programming within the artificial intelligence field. They are not meant as stand alone applications, but rather as tools for building your own applications. - + <descrip> <label id="ACL2"> <tag/ACL2/ <itemize> - <item>Web site: <htmlurl - url="http://www.cliki.net/ACL2" + <item>Web site: <htmlurl + url="http://www.cliki.net/ACL2" name="www.cliki.net/ACL2"> </itemize> @@ -334,7 +334,7 @@ LICENSE <item>AND/OR breadth tree search.</item> </itemize> - + This library has a corresponding book, "<htmlurl url="http://www.neiu.edu/~kwtracy/ooai-book/" name="Object-Oriented Artificial Intelligence, Using C++">". @@ -364,9 +364,8 @@ LICENSE <label id="Aleph"> <tag/Aleph/ <itemize> - <item>Web site: <htmlurl - url="http://web.comlab.ox.ac.uk/oucl/research/areas/machlearn/Aleph/" - name="web.comlab.ox.ac.uk/oucl/research/areas/machlearn/Aleph/"> + <item>Web site: <htmlurl + url="http://www.cs.ox.ac.uk/activities/machlearn/Aleph/"> </itemize> This document provides reference information on A Learning Engine for @@ -466,8 +465,8 @@ LICENSE <label id="FFLL"> <tag/FFLL/ <itemize> - <item>Web site: <htmlurl - url="http://ffll.sourceforge.net/" + <item>Web site: <htmlurl + url="http://ffll.sourceforge.net/" name="ffll.sourceforge.net"> </itemize> @@ -496,14 +495,12 @@ LICENSE <label id="Fuzzy sets for Ada"> <tag/Fuzzy sets for Ada/ <itemize> - <item>Web site: <htmlurl - url="http://www.dmitry-kazakov.de/ada/fuzzy.htm" - name="www.dmitry-kazakov.de/ada/fuzzy.htm"> - <item>Freshmeat: <htmlurl - url="http://freshmeat.net/projects/fuzzy/" - name="freshmeat.net/projects/fuzzy/"> + <item>Web site: <htmlurl + url="http://www.dmitry-kazakov.de/ada/fuzzy.htm"> + <item>Freshmeat: <htmlurl + url="http://freshmeat.net/projects/fuzzy/"> </itemize> - + Fuzzy sets for Ada is a library providing implementations of confidence factors with the operations not, and, or, xor, +, and *, classical fuzzy sets with the set-theoretic operations and the operations of the @@ -597,15 +594,15 @@ LICENSE <label id="LingPipe"> <tag/LingPipe/ <itemize> - <item>Web site: <htmlurl - url="http://www.alias-i.com/lingpipe/"> + <item>Web site: <htmlurl + url="http://alias-i.com/lingpipe/"> </itemize> - + LingPipe is a state-of-the-art suite of natural language processing tools written in Java that performs tokenization, sentence detection, named entity detection, coreference resolution, classification, clustering, part-of-speech tagging, general chunking, fuzzy dictionary - matching. + matching. <label id="Logfun"> @@ -767,7 +764,7 @@ LICENSE <label id="PyCLIPS"> <tag/PyCLIPS/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://pyclips.sourceforge.net/web/"> </itemize> @@ -777,27 +774,6 @@ LICENSE inference engine. - <label id="PyIE"> - <tag/PyIE/ - <itemize> - <item>Subversion repository: <htmlurl - url="https://www.dfwpython.org/repo/Projects/PyIE/"> - </itemize> - - PyIE is a hypothesis based, agenda driven, object oriented inference - engine written in Python. Inferencing modes include back chaining, - opportunistic forward chaining and explicit forward chaining. The - first-class object base supports metaclasses, classes, objects and - multiple, dynamic inheritance. All objects are first class objects and - all attributes are slot values, i.e. data members attached to some - object. - - PyIE uses a TMS (truth maintenance system) for first level (condition - change) non-monotonic reasoning. User defined metaclasses are being - explored to support second level (belief change) non-monotonic - reasoning. - - <label id="Pyke"> <tag/Pyke/ <itemize> @@ -855,10 +831,10 @@ LICENSE <label id="Reverend"> <tag/Reverend/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://sourceforge.net/projects/reverend/"> </itemize> - + Reverned is a general purpose Bayesian classifier written in Python. It is designed to be easily extended to any application domain. @@ -866,14 +842,11 @@ LICENSE <label id="Screamer"> <tag/Screamer/ <itemize> - <item>Web site: <htmlurl - url="http://www.cis.upenn.edu/˜screamer-tools/home.html" - name="www.cis.upenn.edu/˜screamer-tools/home.html"> - <item>Latest version is part of CLOCC: <htmlurl + <item>Latest version is part of CLOCC: <htmlurl url="http://clocc.sourceforge.net/" name="clocc.sourceforge.net"> </itemize> - + Screamer is an extension of Common Lisp that adds support for nondeterministic programming. Screamer consists of two levels. The basic nondeterministic level adds support for @@ -889,48 +862,11 @@ LICENSE extensions to Common Lisp such as CLOS, CLIM and Iterate. - <label id="Shogun"> - <tag/Shogun/ - <itemize> - <item>Web site: <htmlurl - url="http://www.shogun-toolbox.org/"> - </itemize> - - The machine learning toolbox's focus is on large scale kernel methods - and especially on Support Vector Machines (SVM) [1]. It provides a - generic SVM object interfacing to several different SVM - implementations, among them the state of the art LibSVM [2] and - SVMLight [3]. Each of the SVMs can be combined with a variety of - kernels. The toolbox not only provides efficient implementations of the - most common kernels, like the Linear, Polynomial, Gaussian and Sigmoid - Kernel but also comes with a number of recent string kernels as e.g. - the Locality Improved [4], Fischer [5], TOP [6], Spectrum [7], Weighted - Degree Kernel (with shifts) [8] [9] [10]. For the latter the efficient - LINADD [10] optimizations are implemented. Also SHOGUN offers the - freedom of working with custom pre-computed kernels. One of its key - features is the combined kernel which can be constructed by a weighted - linear combination of a number of sub-kernels, each of which not - necessarily working on the same domain. An optimal sub-kernel weighting - can be learned using Multiple Kernel Learning [11] [12] [16]. Currently - SVM 2-class classification and regression problems can be dealt with. - However SHOGUN also implements a number of linear methods like Linear - Discriminant Analysis (LDA), Linear Programming Machine (LPM), (Kernel) - Perceptrons and features algorithms to train hidden markov models. The - input feature-objects can be dense, sparse or strings and of type - int/short/double/char and can be converted into different feature - types. Chains of preprocessors (e.g. substracting the mean) can be - attached to each feature object allowing for on-the-fly pre-processing. - - SHOGUN is implemented in C++ and interfaces to Matlab(tm), R, Octave - and Python. - - <label id="SPASS"> <tag/SPASS/ <itemize> - <item>Web site: <htmlurl - url="http://spass.mpi-sb.mpg.de/" - name="spass.mpi-sb.mpg.de"> + <item>Web site: <htmlurl + url="http://www.spass-prover.org/"> </itemize> SPASS: An Automated Theorem Prover for First-Order Logic with Equality @@ -941,51 +877,39 @@ LICENSE offer you the right functionality. - <label id="ThoughtTreasure"> - <tag/ThoughtTreasure/ - <itemize> - <item>Web site: <htmlurl - url="http://www.signiform.com/tt/htm/tt.htm" - name="www.signiform.com/tt/htm/tt.htm"> - </itemize> - - ThoughtTreasure is a project to create a database of commonsense rules - for use in any application. It consists of a database of a little over - 100K rules and a C API to integrate it with your applications. Python, - Perl, Java and TCL wrappers are already available. - <label id="Torch"> <tag/Torch/ <itemize> - <item>Web site: <htmlurl - url="http://www.torch.ch/" + <item>Web site: <htmlurl + url="http://www.torch.ch/" name="www.torch.ch"> + <item>Successor: <ref id="Torch5"> </itemize> - + Torch is a machine-learning library, written in C++. Its aim is to provide the state-of-the-art of the best algorithms. It is, and it will be, in development forever. - + <itemize> <item>Many gradient-based methods, including multi-layered perceptrons, radial basis functions, and mixtures of experts. Many small "modules" (Linear module, Tanh module, SoftMax module, ...) can be plugged together. - + <item>Support Vector Machine, for classification and regression. - + <item>Distribution package, includes Kmeans, Gaussian Mixture Models, Hidden Markov Models, and Bayes Classifier, and classes for - speech recognition with embedded training. - + speech recognition with embedded training. + <item>Ensemble models such as Bagging and Adaboost. <item>Non-parametric models such as K-nearest-neighbors, Parzen Regression and Parzen Density Estimator. - + <item> </itemize> - + Torch is an open library whose authors encourage everybody to develop new packages to be included in future versions on the official website. @@ -994,26 +918,24 @@ LICENSE <sect1>AI software kits, applications, etc. <p> - + These are various applications, software kits, etc. meant for research in the field of artificial intelligence. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package. - + <descrip> - + <label id="ASA"> <tag/ASA - Adaptive Simulated Annealing/ - <itemize> - <item>Web site: <htmlurl url="http://www.ingber.com/#ASA-CODE" name="www.ingber.com/#ASA-CODE"> - <item>FTP site: <htmlurl url="ftp://ftp.ingber.com/" name="ftp.ingber.com/"> + <itemize> + <item>Web site: <htmlurl url="http://www.ingber.com/#ASA-CODE"> </itemize> - - ASA (Adaptive Simulated Annealing) is a powerful global - optimization C-code algorithm especially useful for nonlinear and/or - stochastic systems. - + + ASA (Adaptive Simulated Annealing) is a powerful global + optimization C-code algorithm especially useful for nonlinear and/or + stochastic systems. ASA is developed to statistically find the best global fit of a nonlinear non-convex cost-function over a D-dimensional space. This @@ -1022,32 +944,30 @@ LICENSE The introduction of re-annealing also permits adaptation to changing sensitivities in the multi-dimensional parameter-space. This annealing schedule is faster than fast Cauchy annealing, where T = T_0/k, - and much faster than Boltzmann annealing, where T = T_0/ln k. + and much faster than Boltzmann annealing, where T = T_0/ln k. - <label id="Babylon"> + <label id="Babylon"> <tag/Babylon/ <itemize> - <item>Archive: <htmlurl + <item>Archive: <htmlurl url="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/expert/systems/babylon/"> - <item>(Dead) FTP site: <htmlurl - url="ftp://ftp.gmd.de/gmd/ai-research/Software/Babylon/"> </itemize> - + BABYLON is a modular, configurable, hybrid environment for developing expert systems. Its features include objects, rules with forward and backward chaining, logic (Prolog) and constraints. BABYLON is implemented and embedded in Common Lisp. - - + + <label id="cfengine"> <tag/cfengine/ <itemize> - <item>Web site: <htmlurl - url="http://www.iu.hio.no/cfengine/" + <item>Web site: <htmlurl + url="http://www.iu.hio.no/cfengine/" name="www.iu.hio.no/cfengine/"> </itemize> - + Cfengine, or the configuration engine is a very high level language for building expert systems which administrate and configure large computer networks. Cfengine uses the idea of classes and a primitive form of @@ -1059,14 +979,14 @@ LICENSE <label id="CLIPS"> <tag/CLIPS/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://clipsrules.sourceforge.net/"> </itemize> - + CLIPS is a productive development and delivery expert system tool which provides a complete environment for the construction of rule - and/or object based expert systems. - + and/or object based expert systems. + CLIPS provides a cohesive tool for handling a wide variety of knowledge with support for three different programming paradigms: rule-based, object-oriented and procedural. Rule-based programming @@ -1077,15 +997,15 @@ LICENSE other systems or to create new components). The procedural programming capabilities provided by CLIPS are similar to capabilities found in languages such as C, Pascal, Ada, and LISP. - + <label id="EMA-XPS"> <tag/EMA-XPS - A Hybrid Graphic Expert System Shell/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://ema-xps.org/"> </itemize> - + EMA-XPS is a hybrid graphic expert system shell based on the ASCII-oriented shell Babylon 2.3 of the German National Research Center for Computer Sciences (GMD). In addition to Babylon's AI-power @@ -1098,10 +1018,10 @@ LICENSE <label id="Eprover"> <tag/Eprover/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.eprover.org/" name="http://www.eprover.org/"> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www4.informatik.tu-muenchen.de/˜schulz/WORK/eprover.html" name="http://www4.informatik.tu-muenchen.de/˜schulz/WORK/eprover.html"> </itemize> @@ -1154,8 +1074,7 @@ LICENSE <label id="FreeHAL"> <tag/FreeHAL/ <itemize> - <item>Web site: <htmlurl - url="http://en.freehal.org/"> + <item>Web site: <htmlurl url="https://freehal.net"> </itemize> FreeHAL is a self-learning conversation simulator which uses semantic @@ -1169,22 +1088,18 @@ LICENSE <label id="FUF-SURGE"> <tag/FUF and SURGE/ <itemize> - <item>Web site: <htmlurl - url="http://www.cs.bgu.ac.il/research/projects/surge/index.htm" - name="www.cs.bgu.ac.il/research/projects/surge/index.htm"> - <item>FTP site: <htmlurl - url="ftp://ftp.cs.bgu.ac.il/pub/fuf/" - name="ftp.cs.bgu.ac.il/pub/fuf/"> + <item>Web site: <htmlurl + url="http://www.cs.bgu.ac.il/surge/index.html"> </itemize> - + FUF is an extended implementation of the formalism of functional unification grammars (FUGs) introduced by Martin Kay specialized to the task of natural language generation. It adds the following features to the base formalism: - <itemize> - <item>Types and inheritance. - <item>Extended control facilities (goal freezing, intelligent - backtracking). + <itemize> + <item>Types and inheritance. + <item>Extended control facilities (goal freezing, intelligent + backtracking). <item>Modular syntax. </itemize> These extensions allow the development of large grammars which can be @@ -1194,14 +1109,14 @@ LICENSE generation component in a larger generation system that encapsulates a rich knowledge of English syntax. SURGE can also be used as a platform for exploration of grammar writing with a generation perspective. - + <label id="GATE"> <tag/GATE/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://gate.ac.uk/"> - <item>Alt site: <htmlurl + <item>Alt site: <htmlurl url="http://sourceforge.net/projects/gate"> </itemize> @@ -1210,26 +1125,26 @@ LICENSE embedding Human Language Technology. GATE is made up of three elements: - <itemize> + <itemize> <item>An architecture describing how language processing systems are made up of components. <item>A framework (or class library, or SDK), written in Java and tested on Linux, Windoze and Solaris. - <item>A graphical development environment built on the framework. + <item>A graphical development environment built on the framework. </itemize> <label id="Grammar Workbench"> <tag/The Grammar Workbench/ <itemize> - <item>Web site: ??? <htmlurl - url="http://www.cs.kun.nl/agfl/" + <item>Web site: ??? <htmlurl + url="http://www.cs.kun.nl/agfl/" name="www.cs.kun.nl/agfl/"> - </itemize> + </itemize> + + Seems to be obsolete??? Its gone from the site, though its parent + project is still ongoing. - Seems to be obsolete??? Its gone from the site, though its parent - project is still ongoing. - The Grammar Workbench, or GWB for short, is an environment for the comfortable development of Affix Grammars in the AGFL-formalism. Its purposes are: @@ -1309,8 +1224,8 @@ LICENSE <label id="LISA"> <tag/LISA/ <itemize> - <item>Web site: <htmlurl - url="http://lisa.sourceforge.net/" + <item>Web site: <htmlurl + url="http://lisa.sourceforge.net/" name="lisa.sourceforge.net"> </itemize> @@ -1324,8 +1239,8 @@ LICENSE <label id="Livingstone2"> <tag/Livingstone2/ <itemize> - <item>Web site: <htmlurl - url="http://ic.arc.nasa.gov/projects/L2/doc/"> + <item>Web site: <htmlurl + url="http://ti.arc.nasa.gov/opensource/projects/livingstone2/"> </itemize> Livingstone2 (L2) is a reusable artificial intelligence (AI) software @@ -1338,9 +1253,8 @@ LICENSE <label id="NICOLE"> <tag/NICOLE/ <itemize> - <item>Web site: <htmlurl - url="http://nicole.sourceforge.net/" - name="nicole.sourceforge.net"> + <item>Web site: <htmlurl + url="http://nicole.sourceforge.net/"> </itemize> NICOLE (Nearly Intelligent Computer Operated Language Examiner) is a @@ -1353,16 +1267,15 @@ LICENSE stored in it's database. Each new sentence that has been typed in, and NICOLE doesn't know about, is included into NICOLE's database, thus extending the knowledge base of NICOLE. - + <label id="Otter"> <tag/Otter: An Automated Deduction System/ <itemize> - <item>Web site: <htmlurl - url="http://www-unix.mcs.anl.gov/AR/otter/" - name="www-unix.mcs.anl.gov/AR/otter/"> + <item>Web site: <htmlurl + url="http://www-unix.mcs.anl.gov/AR/otter/"> </itemize> - + Our current automated deduction system Otter is designed to prove theorems stated in first-order logic with equality. Otter's inference rules are based on resolution and paramodulation, and it @@ -1414,17 +1327,17 @@ LICENSE name="sitemaker.umich.edu/soar"> </itemize> - + Soar has been developed to be a general cognitive architecture. We intend ultimately to enable the Soar architecture to: - <itemize> + <itemize> <item>work on the full range of tasks expected of an intelligent agent, from highly routine to extremely difficult, open-ended problems <item>represent and use appropriate forms of knowledge, such as procedural, declarative, episodic, and possibly iconic - <item>employ the full range of problem solving methods - <item>interact with the outside world and + <item>employ the full range of problem solving methods + <item>interact with the outside world and <item>learn about all aspects of the tasks and its performance on them. </itemize> In other words, our intention is for Soar to support all the @@ -1433,12 +1346,8 @@ LICENSE <label id="TCM"> <tag/TCM/ <itemize> - <item>Web site: <htmlurl - url="http://wwwhome.cs.utwente.nl/˜tcm/" - name="wwwhome.cs.utwente.nl/˜tcm/"> - <item>FTP site: <htmlurl - url="ftp://ftp.cs.utwente.nl/pub/tcm/" - name="ftp.cs.utwente.nl/pub/tcm/"> + <item>Web site: <htmlurl + url="http://wwwhome.cs.utwente.nl/˜tcm/"> </itemize> TCM (Toolkit for Conceptual Modeling) is our suite of graphical @@ -1450,19 +1359,19 @@ LICENSE editor and a Function Decomposition table editor. TCM is easy to use and performs numerous consistency checks, some of them immediately, some of them upon request. - + <label id="Yale"> <tag/Yale/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://yale.sf.net/" name="yale.sf.net/"> - <item>Alt Web site: <htmlurl + <item>Alt Web site: <htmlurl url="http://rapid-i.com/" name="rapid-i.com/"> </itemize> - + YALE (Yet Another Learning Environment) is an environment for machine learning experiments. Experiments can be made up of a large number of arbitrarily nestable operators and their setup is described by XML @@ -1471,7 +1380,7 @@ LICENSE <label id="WEKA"> - <tag/WEKA/ + <tag/WEKA/ <itemize> <item>Web site: <htmlurl url="http://www.cs.waikato.ac.nz/˜ml/" @@ -1509,7 +1418,7 @@ LICENSE a great deal of success with image processing and robot control. - + <sect1>Connectionist class/code libraries <p> @@ -1524,7 +1433,7 @@ LICENSE <itemize> <item>Web site: <htmlurl url="http://www.cs.utoronto.ca/˜radford/fbm.software.html" name="www.cs.utoronto.ca/˜radford/fbm.software.html"> </itemize> - + This software implements flexible Bayesian models for regression and classification applications that are based on multilayer perceptron neural networks or on Gaussian processes. The @@ -1533,13 +1442,13 @@ LICENSE distribution, and may be useful in other applications. - <label id="BELIEF"> + <label id="BELIEF"> <tag/BELIEF/ <itemize> <item>Web site: <htmlurl url="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/reasonng/probabl/belief/" name="www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/reasonng/probabl/belief/"> </itemize> - - + + BELIEF is a Common Lisp implementation of the Dempster and Kong fusion and propagation algorithm for Graphical Belief Function Models and the Lauritzen and Spiegelhalter algorithm for @@ -1552,12 +1461,12 @@ LICENSE both probability distributions and belief functions. It also has limited support for second order models (probability distributions on parameters). - + <label id="bpnn.py"> <tag/bpnn.py/ <itemize> - <item>Web site: <htmlurl - url="http://arctrix.com/nas/python/bpnn.py" + <item>Web site: <htmlurl + url="http://arctrix.com/nas/python/bpnn.py" name="http://arctrix.com/nas/python/bpnn.py"> </itemize> @@ -1610,11 +1519,11 @@ LICENSE <label id="CNNs"> <tag/CNNs/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.isiweb.ee.ethz.ch/haenggi/CNNsim.html"> - <item>Newer Version: <htmlurl + <item>Newer Version: <htmlurl url="http://www.isiweb.ee.ethz.ch/haenggi/CNNsim_adv_manual.html"> - <item>Old Page: <htmlurl + <item>Old Page: <htmlurl url="http://www.ce.unipr.it/research/pardis/CNN/cnn.html"> </itemize> @@ -1626,23 +1535,40 @@ LICENSE for those people who are not experienced in CNN theory. - <label id="CONICAL"> - <tag/CONICAL/ - <itemize> - <item>Web site: <htmlurl - url="http://strout.net/conical/" name="strout.net/conical/"> - </itemize> - - CONICAL is a C++ class library for building simulations common - in computational neuroscience. Currently its focus is on - compartmental modeling, with capabilities similar to GENESIS and - NEURON. A model neuron is built out of compartments, usually - with a cylindrical shape. When small enough, these open-ended - cylinders can approximate nearly any geometry. Future classes - may support reaction-diffusion kinetics and more. A key feature - of CONICAL is its cross-platform compatibility; it has been - fully co-developed and tested under Unix, DOS, and Mac OS. - + <label id="CONICAL"> + <tag/CONICAL/ + <itemize> + <item>Web site: <htmlurl + url="http://strout.net/conical/" name="strout.net/conical/"> + </itemize> + + CONICAL is a C++ class library for building simulations common + in computational neuroscience. Currently its focus is on + compartmental modeling, with capabilities similar to GENESIS and + NEURON. A model neuron is built out of compartments, usually + with a cylindrical shape. When small enough, these open-ended + cylinders can approximate nearly any geometry. Future classes + may support reaction-diffusion kinetics and more. A key feature + of CONICAL is its cross-platform compatibility; it has been + fully co-developed and tested under Unix, DOS, and Mac OS. + + + <label id="Encog"> + <tag/Encog/ + <itemize> + <item>Web site: <htmlurl + url="http://www.heatonresearch.com/"> + </itemize> + + Encog is an advanced neural network and machine learning framework. + Encog contains classes to create a wide variety of networks, as well as + support classes to normalize and process data for these neural + networks. Encog trains using multithreaded resilient propagation. Encog + can also make use of a GPU to further speed processing time. A GUI + based workbench is also provided to help model and train neural + networks. Encog has been in active development since 2008. Encog is + available for Java, .Net and Silverlight. + <label id="FANN"> <tag/FANN/ @@ -1666,7 +1592,7 @@ LICENSE <label id="ffnet"> <tag/ffnet/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://ffnet.sourceforge.net/"> </itemize> @@ -1679,9 +1605,8 @@ LICENSE <label id="Joone"> <tag/Joone/ <itemize> - <item>Web site: <htmlurl - url="http://www.jooneworld.com/" - name="www.jooneworld.com"> + <item>Web site: <htmlurl + url="http://sourceforge.net/projects/joone/"> </itemize> Joone is a neural net framework to create, train and test neural nets. @@ -1699,11 +1624,11 @@ LICENSE <label id="Matrix Class"> <tag/Matrix Class/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.cs.ucla.edu/pub/" + <item>FTP site: <htmlurl + url="ftp://ftp.cs.ucla.edu/pub/" name="ftp.cs.ucla.edu/pub/"> </itemize> - + A simple, fast, efficient C++ Matrix class designed for scientists and engineers. The Matrix class is well suited for applications with complex math algorithms. As an demonstration @@ -1712,26 +1637,12 @@ LICENSE neural network. - <label id="Neural Networks at your Fingertips"> - <tag/Neural Networks at your Fingertips/ - <itemize> - <item>Web site: <htmlurl - url="http://www.neural-networks-at-your-fingertips.com/" - name="www.neural-networks-at-your-fingertips.com"> - </itemize> - - A set of ANSI C packages that illustrate Adaline networks, - back-propagation, the Hopfield model, BAM, Boltzman, CPN, SOM, and - ART1. Coded in portable, self-contained ANSI C. With complete example - applications from a variety of well-known application domains. - - <label id="NEAT"> <tag/NEAT/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://nn.cs.utexas.edu/project-view.php?RECORD_KEY(Projects)=ProjID&ProjID(Projects)=14"> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.cs.ucf.edu/˜kstanley/neat.html"> </itemize> @@ -1754,43 +1665,26 @@ LICENSE evolution of connecting neurons between them. - <label id="NEURObjects"> - <tag/NEURObjects/ + <label id="NeuroLab"> + <tag/NeuroLab/ <itemize> - <item>Web site: <htmlurl - url="http://www.disi.unige.it/person/ValentiniG/NEURObjects/" - name="www.disi.unige.it/person/ValentiniG/NEURObjects/"> + <item>Web site: <htmlurl + url="http://packages.python.org/neurolab/"> </itemize> - NEURObjects is a set of C++ library classes for neural networks - development. The main goal of the library consists in supporting - researchers and practitioners in developing new neural network methods - and applications, exploiting the potentialities of object-oriented - design and programming. NEURObjects provides also general purpose - applications for classification problems and can be used for fast - prototyping of inductive machine learning applications. - - - <label id="NuPIC"> - <tag/NuPIC/ - <itemize> - <item>Web site: <htmlurl - url="http://www.numenta.com/"> - </itemize> - - The Numenta Platform for Intelligent Computing (NuPIC) is built around - HTM networds (Hierarchical Temporal Memory). Based on Jeff Hawkins idea - as laid out in his On Intelligence book. NuPIC consists of the Numenta - Tools Framework and the Numenta Runtime Engine. - - Free for non-commercial use. + NeuroLab - a library of basic neural networks algorithms with flexible + network configurations and learning algorithms for Python. To simplify + the using of the library, interface is similar to the package of Neural + Network Toolbox (NNT) of MATLAB (c). The library is based on the + package numpy (http://numpy.scipy.org), some learning algorithms are + used scipy.optimize (http://scipy.org). <label id="Pulcinella"> <tag/Pulcinella/ <itemize> - <item>Web site: <htmlurl - url="http://iridia.ulb.ac.be/pulcinella/" + <item>Web site: <htmlurl + url="http://iridia.ulb.ac.be/pulcinella/" name="iridia.ulb.ac.be/pulcinella/"> </itemize> @@ -1804,13 +1698,13 @@ LICENSE Dempster-Shafer's theory of belief functions; and the possibility theory by Zadeh, Dubois and Prade's. A User's Manual is available on request. - + <label id="scnANNlib"> <tag/scnANNlib/ <itemize> - <item>Web site: <htmlurl - url="http://www.sentinelchicken.org/projects/scnANNlib/" + <item>Web site: <htmlurl + url="http://www.sentinelchicken.org/projects/scnANNlib/" name="www.sentinelchicken.org/projects/scnANNlib/"> </itemize> @@ -1819,13 +1713,13 @@ LICENSE library supports non-recursive networks with an arbitrary number of layers, each with an arbitrary number of nodes. Facilities exist for training with momentum, and there are plans to gracefully extend the - functionality of the library in later releases. + functionality of the library in later releases. <label id="UTCS"> <tag/UTCS Neural Nets Research Group Software/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://nn.cs.utexas.edu/soft-list.php"> </itemize> @@ -1846,7 +1740,7 @@ LICENSE <item>PROC - Parsing, generation, question answering <item>HFM - Episodic memory organization <item>DISLEX - Lexical processing - <item>DISCERN - The full integrated model + <item>DISCERN - The full integrated model </itemize> <item>FGREPNET - Learning distributed representations </itemize> @@ -1879,21 +1773,21 @@ LICENSE <label id="C++ ANNs"> <tag/Various (C++) Neural Networks/ - <itemize> - <item>Web site: <htmlurl - url="http://www.dontveter.com/nnsoft/nnsoft.html" + <itemize> + <item>Web site: <htmlurl + url="http://www.dontveter.com/nnsoft/nnsoft.html" name="www.dontveter.com/nnsoft/nnsoft.html"> </itemize> - + Example neural net codes from the book, <htmlurl url="http://www.dontveter.com/basisofai/basisofai.html" name="The Pattern Recognition Basics of AI">. These are simple example codes of these various neural nets. They work well as a good starting point for simple experimentation and for learning what the code is like behind the - simulators. The types of networks available on this site are: + simulators. The types of networks available on this site are: (implemented in C++) - + <itemize> <item>The Backprop Package <item>The Nearest Neighbor Algorithms @@ -1904,45 +1798,43 @@ LICENSE <item>Bi-Directional Associative Memory <item>The Feedforward Counter-Propagation Network </itemize> - </descrip> - + <sect1>Connectionist software kits/applications <p> - + These are various applications, software kits, etc. meant for research in the field of Connectionism. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package. <descrip> - + <label id="Aspirin-MIGRANES"> <tag/Aspirin - MIGRAINES/ (am6.tar.Z on ftp site) <itemize> <item>FTP site: <htmlurl url="ftp://sunsite.unc.edu/pub/academic/computer-science/neural-networks/programs/Aspirin/" name="sunsite.unc.edu/pub/academic/computer-science/neural-networks/programs/Aspirin/"> </itemize> - - The software that we are releasing now is for creating, - and evaluating, feed-forward networks such as those used with the - backpropagation learning algorithm. The software is aimed both at + + The software that we are releasing now is for creating, + and evaluating, feed-forward networks such as those used with the + backpropagation learning algorithm. The software is aimed both at the expert programmer/neural network researcher who may wish to tailor significant portions of the system to his/her precise needs, as well as at casual users who will wish to use the system with an absolute minimum of effort. - + <label id="DDLab"> - <tag/DDLab/ + <tag/DDLab/ <itemize> - <item>Web site: <htmlurl url="http://www.santafe.edu/˜wuensch/ddlab.html" name="www.santafe.edu/˜wuensch/ddlab.html"> - <item>FTP site: <htmlurl url="ftp://ftp.santafe.edu/pub/wuensch/" name="ftp.santafe.edu/pub/wuensch/"> + <item>Web site: <htmlurl url="http://www.ddlab.com/"> </itemize> - + DDLab is an interactive graphics program for research into the dynamics of finite binary networks, relevant to the study of complexity, emergent phenomena, neural networks, and aspects of @@ -1952,18 +1844,41 @@ LICENSE connections and heterogeneous rules). The network may also have heterogeneous neighborhood sizes. - - <label id="GENESIS"> - <tag/GENESIS/ + + <label id="Emergent"> + <tag/Emergent/ <itemize> - <item>Web site: <htmlurl - url="http://www.genesis-sim.org/GENESIS/" - name="www.genesis-sim.org/GENESIS/"> - <item>FTP site: <htmlurl - url="ftp://genesis-sim.org/pub/genesis/" - name="genesis-sim.org/pub/genesis/"> - </itemize> - + <item>Web site: <htmlurl + url="http://grey.colorado.edu/emergent/index.php/Main_Page"> + </itemize> + + Note: this is a descendant of <ref id="PDP++"> + + emergent is a comprehensive, full-featured neural network simulator + that allows for the creation and analysis of complex, sophisticated + models of the brain in the world. With an emphasis on qualitative + analysis and teaching, it also supports the workflow of professional + neural network researchers. The GUI environment allows users to quickly + construct basic networks, modify the input/output patterns, + automatically generate the basic programs required to train and test + the network, and easily utilize several data processing and network + analysis tools. In addition to the basic preset network train and test + programs, the high level drag-and-drop programming interface, built on + top of a scripting language that has full introspective access to all + aspects of networks and the software itself, allows one to write + programs that seamlessly weave together the training of a network and + evolution of its environment without ever typing out a line of code. + Networks and all of their state variables are visually inspected in 3D, + allowing for a quick "visual regression" of network dynamics and robot + behavior. + + + <label id="GENESIS"> + <tag/GENESIS/ + <itemize> + <item>Web site: <htmlurl url="http://genesis-sim.org/"> + </itemize> + GENESIS (short for GEneral NEural SImulation System) is a general purpose simulation platform which was developed to support the simulation of neural systems ranging from complex @@ -1976,61 +1891,87 @@ LICENSE systems. Although the software can also model more abstract networks, other simulators are more suitable for backpropagation and similar connectionist modeling. - - + <label id="JavaBayes"> <tag/JavaBayes/ <itemize> - <item>Web site: <htmlurl url="http://www.cs.cmu.edu/People/javabayes/index.html/" name="www.cs.cmu.edu/People/javabayes/index.html/"> + <item>Web site: <htmlurl + url="http://www.cs.cmu.edu/~javabayes/"> </itemize> - The JavaBayes system is a set of tools, containing a graphical editor, a core inference engine and a parser. JavaBayes can produce: - <itemize> + <itemize> <item> the marginal distribution for any variable in a network. - <item> the expectations for univariate functions (for example, + <item> the expectations for univariate functions (for example, expected value for variables). - <item> configurations with maximum a posteriori probability. - <item> configurations with maximum a posteriori expectation for + <item> configurations with maximum a posteriori probability. + <item> configurations with maximum a posteriori expectation for univariate functions. </itemize> - <label id="Jbpe"> <tag/Jbpe/ <itemize> - <item>Web site: <htmlurl - url="http://cs.felk.cvut.cz/˜koutnij/studium/jbpe.html" + <item>Web site: <htmlurl + url="http://cs.felk.cvut.cz/˜koutnij/studium/jbpe.html" name="cs.felk.cvut.cz/˜koutnij/studium/jbpe.html"> </itemize> Jbpe is a back-propagation neural network editor/simulator. - Features + Features <itemize> - <item>Standart back-propagation networks creation. - <item>Saving network as a text file, which can be edited and loaded - back. - <item>Saving/loading binary file - <item>Learning from a text file (with structure specified below), + <item>Standart back-propagation networks creation. + <item>Saving network as a text file, which can be edited and loaded + back. + <item>Saving/loading binary file + <item>Learning from a text file (with structure specified below), number of learning periods / desired network energy can be - specified as a criterion. - <item>Network recall + specified as a criterion. + <item>Network recall </itemize> + <label id="Nengo"> + <tag/Nengo/ + <itemize> + <item>Web site: <htmlurl + url="http://www.nengo.ca/"> + </itemize> + + Nengo (Nengo Neural Simulator) is a graphical and scripting based + software package for simulating large-scale neural systems. + + To use it, you define groups of neurons in terms of what they + represent, and then form connections between neural groups in terms of + what computation should be performed on those representations. Nengo + then uses the Neural Engineering Framework (NEF) to solve for the + appropriate synaptic connection weights to achieve this desired + computation. Nengo also supports various kinds of learning. Nengo helps + make detailed spiking neuron models that implement complex high-level + cognitive algorithms. + + Among other things, Nengo has been used to implement motor control, + visual attention, serial recall, action selection, working memory, + attractor networks, inductive reasoning, path integration, and planning + with problem solving. + + The Spaun <htmlurl url="http://models.nengo.ca/spaun"> neural simulator + is implemented in Nengo and its source is available as well. + + <label id="NN Generator"> - <tag/Neural Network Generator/ + <tag/Neural Network Generator/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.idsia.ch/pub/rafal/" + <item>FTP site: <htmlurl + url="ftp://ftp.idsia.ch/pub/rafal/" name="ftp.idsia.ch/pub/rafal"> </itemize> - + The Neural Network Generator is a genetic algorithm for the topological optimization of feedforward neural networks. It implements the Semantic Changing Genetic Algorithm and the @@ -2039,59 +1980,20 @@ LICENSE adaptation of the genetic coding through population analysis. The Unit-Cluster Model is an approach to the construction of modular feedforward networks with a ''backbone'' - structure. - - NOTE: To compile this on Linux requires one change in the Makefiles. - You will need to change '-ltermlib' to '-ltermcap'. - + structure. - <label id="Neureka ANS"> - <tag/Neureka ANS (nn/xnn)/ - <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.ii.uib.no/pub/neureka/" - name="ftp.ii.uib.no/pub/neureka/"> - </itemize> - - nn is a high-level neural network specification language. The - current version is best suited for feed-forward nets, but - recurrent models can and have been implemented, e.g. Hopfield - nets, Jordan/Elman nets, etc. In nn, it is easy to change - network dynamics. The nn compiler can generate C code or - executable programs (so there must be a C compiler available), - with a powerful command line interface (but everything may also - be controlled via the graphical interface, xnn). It is possible - for the user to write C routines that can be called from inside - the nn specification, and to use the nn specification as a - function that is called from a C program. Please note that no - programming is necessary in order to use the network models that - come with the system (`netpack'). - - - xnn is a graphical front end to networks generated by the nn - compiler, and to the compiler itself. The xnn graphical - interface is intuitive and easy to use for beginners, yet - powerful, with many possibilities for visualizing network data. - - - NOTE: You have to run the install program that comes with this - to get the license key installed. It gets put (by default) in - /usr/lib. If you (like myself) want to install the package - somewhere other than in the /usr directory structure (the - install program gives you this option) you will have to set up - some environmental variables (NNLIBDIR & NNINCLUDEDIR are - required). You can read about these (and a few other optional - variables) in appendix A of the documentation (pg 113). + NOTE: To compile this on Linux requires one change in the Makefiles. + You will need to change '-ltermlib' to '-ltermcap'. <label id="NEURON"> - <tag/NEURON/ + <tag/NEURON/ <itemize> - <item>Web site: <htmlurl - url="http://www.neuron.yale.edu/" + <item>Web site: <htmlurl + url="http://www.neuron.yale.edu/" name="www.neuron.yale.edu/"> </itemize> - + NEURON is an extensible nerve modeling and simulation program. It allows you to create complex nerve models by connecting multiple one-dimensional sections together to form @@ -2101,7 +2003,7 @@ LICENSE designed to present the neural modeler with a intuitive environment and hide the details of the numerical methods used in the simulation. - + <label id="Neuroph"> <tag/Neuroph/ @@ -2116,21 +2018,18 @@ LICENSE basic NN concepts. Also has nice GUI neural network editor to quickly create Java neural network components. - + <label id="PDP++"> <tag/PDP++/ <itemize> <item>Web site: <htmlurl - url="http://www.cnbc.cmu.edu/Resources/PDP++/" - name="www.cnbc.cmu.edu/Resources/PDP++/"> - <item>FTP site (US): <htmlurl - url="ftp://cnbc.cmu.edu/pub/pdp++/" - name="cnbc.cmu.edu/pub/pdp++/"> + url="http://archive.cnbc.cmu.edu/Resources/PDP++/PDP++.html"> <item>FTP mirror (US): <htmlurl - url="ftp://grey.colorado.edu/pub/oreilly/pdp++/" - name="grey.colorado.edu/pub/oreilly/pdp++/"> + url="ftp://grey.colorado.edu/pub/oreilly/pdp++/"> </itemize> - + + NOTE: Renamed to <ref id="Emergent"> + As the field of Connectionist modeling has grown, so has the need for a comprehensive simulation environment for the development and testing of Connectionist models. Our goal in developing PDP++ has been @@ -2149,53 +2048,50 @@ LICENSE creates new C++ objects, which might be new kinds of units or new kinds of processes; once compiled and linked into the simulator, these new objects can then be accessed and used like any other. - <label id="RNS"> - <tag/RNS/ + <tag/RNS/ <itemize> <item>Web site: <htmlurl url="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/neural/systems/rns/" name="www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/neural/systems/rns/"> </itemize> - + RNS (Recurrent Network Simulator) is a simulator for recurrent neural networks. Regular neural networks are also supported. The program uses a derivative of the back-propagation algorithm, but also includes other (not that well tested) algorithms. - + Features include - <itemize> + <itemize> <item>freely choosable connections, no restrictions besides memory or CPU constraints <item>delayed links for recurrent networks <item>fixed values or thresholds can be specified for weights - <item>(recurrent) back-propagation, Hebb, differential Hebb, - simulated annealing and more - <item>patterns can be specified with bits, floats, characters, - numbers, and random bit patterns with Hamming distances can + <item>(recurrent) back-propagation, Hebb, differential Hebb, + simulated annealing and more + <item>patterns can be specified with bits, floats, characters, + numbers, and random bit patterns with Hamming distances can be chosen for you <item>user definable error functions <item>output results can be used without modification as input </itemize> - - + + <label id="Python Smantic Nets"> <tag/Semantic Networks in Python/ <itemize> <item>Web site: <htmlurl url="http://strout.net/info/coding/python/ai/index.html" name="strout.net/info/coding/python/ai/index.html"> </itemize> - - + The semnet.py module defines several simple classes for building and using semantic networks. A semantic network is a way of representing knowledge, and it enables the program to do simple reasoning with very little effort on the part of the programmer. - The following classes are defined: - <itemize> + <itemize> <item><bf>Entity</bf>: This class represents a noun; it is something which can be related to other things, and about which you can store facts. @@ -2203,27 +2099,22 @@ LICENSE which may exist between two entities. One special relation, "IS_A", is predefined because it has special meaning (a sort of logical inheritance). - <item><bf>Fact</bf>: A Fact is an assertion that a relationship + <item><bf>Fact</bf>: A Fact is an assertion that a relationship exists between two entities. </itemize> <p> - With these three object types, you can very quickly define knowledge + With these three object types, you can very quickly define knowledge about a set of objects, and query them for logical conclusions. - <label id="SNNS"> <tag/SNNS/ <itemize> - <item>Web site: <htmlurl - url="http://www-ra.informatik.uni-tuebingen.de/SNNS/" - name="www-ra.informatik.uni-tuebingen.de/SNNS/"> - <item>FTP site: <htmlurl - url="ftp://ftp.informatik.uni-stuttgart.de/pub/SNNS/" - name="ftp.informatik.uni-stuttgart.de/pub/SNNS/"> + <item>Web site: <htmlurl + url="http://www-ra.informatik.uni-tuebingen.de/SNNS/"> </itemize> - + Stuttgart Neural Net Simulator (version 4.1). An awesome neural net simulator. Better than any commercial simulator I've seen. The simulator kernel is written in C (it's fast!). It supports over 20 @@ -2234,44 +2125,16 @@ LICENSE example networks and tutorials for many of the architectures. ENZO, a supplementary system allows you to evolve your networks with genetic algorithms. - - <label id="SPRLIB-ANNLIB"> - <tag/SPRLIB/ANNLIB/ - <itemize> - <item>Web site: <htmlurl url="http://www.ph.tn.tudelft.nl/˜sprlib/" name="www.ph.tn.tudelft.nl/˜sprlib/"> - </itemize> - - - SPRLIB (Statistical Pattern Recognition Library) was developed - to support the easy construction and simulation of pattern - classifiers. It consist of a library of functions (written in C) - that can be called from your own program. Most of the well-known - classifiers are present (k-nn, Fisher, Parzen, ....), as well as - error estimation and dataset generation routines. - - - ANNLIB (Artificial Neural Networks Library) is a neural network - simulation library based on the data architecture laid down by - SPRLIB. The library contains numerous functions for creating, - training and testing feed-forward networks. Training algorithms - include back-propagation, pseudo-Newton, Levenberg-Marquardt, - conjugate gradient descent, BFGS.... Furthermore, it is possible - - due to the datastructures' general applicability - to build - Kohonen maps and other more exotic network architectures using - the same data types. - - - <label id="TOOLDIAG"> - <tag/TOOLDIAG/ + <tag/TOOLDIAG/ <itemize> - <item>Web site: <htmlurl - url="http://www.inf.ufes.br/˜thomas/home/soft.html" + <item>Web site: <htmlurl + url="http://www.inf.ufes.br/˜thomas/home/soft.html" name="www.inf.ufes.br/˜thomas/home/soft.html"> - <item>Alt site: <htmlurl - url="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/neural/systems/tooldiag/0.html" + <item>Alt site: <htmlurl + url="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/neural/systems/tooldiag/0.html" name="http://www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/neural/systems/tooldiag/0.html"> </itemize> @@ -2281,33 +2144,30 @@ LICENSE features, without any missing values. No symbolic features (attributes) are allowed. The program in implemented in the 'C' programming language and was tested in several computing - environments. - + environments. + <label id="XNBC"> <tag/XNBC/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.b3e.jussieu.fr/xnbc/" name="www.b3e.jussieu.fr/xnbc/"> </itemize> - + XNBC v8 is a simulation tool for the neuroscientists interested in - simulating biological neural networks using a user friendly tool. + simulating biological neural networks using a user friendly tool. - XNBC is a software package for simulating biological neural networks. - - Four neuron models are available, three phenomenologic models (xnbc, - leaky integrator and conditional burster) and an ion-conductance based - model. Inputs to the simulated neurons can be provided by experimental - data stored in files, allowing the creation of `hybrid'' networks. + XNBC is a software package for simulating biological neural networks. + Four neuron models are available, three phenomenologic models (xnbc, + leaky integrator and conditional burster) and an ion-conductance based + model. Inputs to the simulated neurons can be provided by experimental + data stored in files, allowing the creation of `hybrid'' networks. </descrip> - - - + <sect>Evolutionary Computing <label id="Evolutionary Computing"> <p> @@ -2320,10 +2180,10 @@ LICENSE anything from solving some engineering problem to winning a game. - + <sect1>EC class/code libraries <p> - + These are libraries of code or classes for use in programming within the evolutionary computation field. They are not meant as stand alone applications, but rather as tools for building your own applications. @@ -2333,7 +2193,7 @@ LICENSE <label id="ANNEvolve"> <tag/ANNEvolve/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://annevolve.sourceforge.net/" name="annevolve.sourceforge.net"> </itemize> @@ -2381,13 +2241,13 @@ LICENSE <label id="daga"> <tag/daga/ <itemize> - <item>Web site: <htmlurl - url="http://garage.cps.msu.edu/software/daga3.2/" + <item>Web site: <htmlurl + url="http://garage.cps.msu.edu/software/daga3.2/" name="garage.cps.msu.edu/software/daga3.2/"> </itemize> - daga is an experimental release of a 2-level genetic algorithm + daga is an experimental release of a 2-level genetic algorithm compatible with the GALOPPS GA software. It is a meta-GA which dynamically evolves a population of GAs to solve a problem presented to the lower-level GAs. When multiple GAs (with different operators, @@ -2395,18 +2255,36 @@ LICENSE problem, the ones showing better performance have a higher probability of surviving and "breeding" to the next macro-generation (i.e., spawning new "daughter"-GAs with characteristics inherited from the - parental GA or GAs. In this way, we try to encourage good + parental GA or GAs. In this way, we try to encourage good problem-solving strategies to spread to the whole population of GAs. + <label id="DEAP"> + <tag/DEAP/ + <itemize> + <item>Web site: <htmlurl + url="http://deap.googlecode.com"> + </itemize> + + DEAP is intended to be an easy to use distributed evolutionary + algorithm library in the Python language. Its two main components are + modular and can be used separately. The first module is a Distributed + Task Manager (DTM), which is intended to run on cluster of computers + using TCP or a MPI connection. The second part is the Evolutionary + Algorithms in Python (EAP) framework. EAP is the evolutionary core of + DEAP, it provides data structures, methods and tools to design any kind + of evolutionary algorithm. It works in perfect harmony with DTM, + allowing easy parallelization of any demanding evolutionary task. + + <label id="dgpf"> <tag/dgpf/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://dgpf.sourceforge.net/" name="dgpf.sourceforge.net"> </itemize> - + The Distributed Genetic Programming Framework (DGPF) is a scalable Java environment for heuristic, simulation-based search algorithms of any kind and Genetic Algorithms in special. We use the broad foundation of @@ -2499,13 +2377,13 @@ LICENSE Niching (sharing) and an option for the number of children per pair of parents has been added. More recently, an option for the use of a micro-GA has been added. - + <label id="FREVO"> <tag/FREVO/ <itemize> <item>Web site: <htmlurl - url="http://www.frevotool.tk/"> + url="http://frevo.sourceforge.net/"> </itemize> FREVO is an open-source framework developed in Java to help engineers @@ -2519,20 +2397,16 @@ LICENSE <label id="GALib"> - <tag/GAlib: Matthew's Genetic Algorithms Library/ + <tag/GAlib: Matthew's Genetic Algorithms Library/ <itemize> - <item>Web Site: <htmlurl - url="http://lancet.mit.edu/ga/" - name="lancet.mit.edu/ga/"> + <item>Web Site: <htmlurl + url="http://lancet.mit.edu/ga/"> <item>Download: <htmlurl - url="http://lancet.mit.edu/ga/dist/" - name="lancet.mit.edu/ga/dist/"> - <item>Register GAlib at: <htmlurl - url="http://lancet.mit.edu/ga/Register.html" - name="lancet.mit.edu/ga/Register.html"> + url="http://lancet.mit.edu/ga/dist/"> + <item>Register GAlib at: <htmlurl + url="http://lancet.mit.edu/ga/Register.html"> </itemize> - GAlib contains a set of C++ genetic algorithm objects. The library includes tools for using genetic algorithms to do optimization in any C++ program using any representation and genetic @@ -2691,13 +2565,11 @@ LICENSE <itemize> <item>FTP site: <htmlurl url="ftp://ftp.cs.bham.ac.uk/pub/authors/W.B.Langdon/gp-code/"> - <item>Documentation (GPdata-icga-95.ps): <htmlurl - url="ftp://cs.ucl.ac.uk/genetic/papers/"> </itemize> - GPdata-3.0.tar.gz (C++) contains a version of Andy Singleton's + GPdata-3.0.tar.gz (C++) contains a version of Andy Singleton's GP-Quick version 2.1 which has been extensively altered to support: - <itemize> + <itemize> <item>Indexed memory operation (cf. teller) <item>multi tree programs <item>Adfs @@ -2705,10 +2577,10 @@ LICENSE <item>populations partitioned into demes <item>(A version of) pareto fitness </itemize> - This ftp site also contains a small C++ program (ntrees.cc) to - calculate the number of different there are of a given length and + This ftp site also contains a small C++ program (ntrees.cc) to + calculate the number of different there are of a given length and given function and terminal set. - + <label id="Java GP - gpjpp"> <tag/gpjpp Genetic Programming in Java/ @@ -2771,20 +2643,18 @@ LICENSE designed to be highly modular so that more adventurous users can easily plug-in custom genetic operators and other sub-components. - + <label id="lil-gp"> <tag/lil-gp/ <itemize> <item>Web site: <htmlurl - url="http://garage.cps.msu.edu/software/lil-gp/"> - <item>FTP site: <htmlurl - url="ftp://garage.cps.msu.edu/pub/GA/lilgp/"> + url="http://garage.cse.msu.edu/software/lil-gp/"> </itemize> - <tag/patched lil-gp */ + <tag/patched lil-gp */ <itemize> <item>Web site: <htmlurl - url="http://cs.gmu.edu/~sean/research/lil-gp-patch/"> + url="http://cs.gmu.edu/˜sean/research/lil-gp-patch/"> </itemize> lil-gp is a generic 'C' genetic programming tool. It was written @@ -2792,17 +2662,17 @@ LICENSE number of options including: <itemize> <item> Generic 'C' program that runs on UNIX workstations - <item> Support for multiple population experiments, using - arbitrary and user settable topologies for exchange, for - a single processor (i.e., you can do multiple population gp + <item> Support for multiple population experiments, using + arbitrary and user settable topologies for exchange, for + a single processor (i.e., you can do multiple population gp experiments on your PC). - <item> lil-gp manipulates trees of function pointers which are - allocated in single, large memory blocks for speed and to + <item> lil-gp manipulates trees of function pointers which are + allocated in single, large memory blocks for speed and to avoid swapping. </itemize> - * The patched lil-gp kernel is strongly-typed, with modifications on + * The patched lil-gp kernel is strongly-typed, with modifications on multithreading, coevolution, and other tweaks and features. - + <label id="Lithos"> <tag/Lithos/ @@ -2838,12 +2708,7 @@ LICENSE <label id="PGAPack"> <tag/PGAPack/ Parallel Genetic Algorithm Library <itemize> - <item>Web site: <htmlurl - url="http://www-fp.mcs.anl.gov/CCST/research/reports_pre1998/comp_bio/stalk/pgapack.html" - name="www-fp.mcs.anl.gov/CCST/research/reports_pre1998/comp_bio/stalk/pgapack.html"> - <item>FTP site: <htmlurl - url="ftp://ftp.mcs.anl.gov/pub/pgapack/" - name="ftp.mcs.anl.gov/pub/pgapack/"> + <item>FTP site: <htmlurl url="ftp://ftp.mcs.anl.gov/pub/pgapack/"> </itemize> PGAPack is a general-purpose, data-structure-neutral, parallel @@ -2851,31 +2716,31 @@ LICENSE desired in a genetic algorithm library, in an integrated, seamless, and portable manner. Key features are in PGAPack V1.0 include: <itemize> - <item>Callable from Fortran or C. + <item>Callable from Fortran or C. <item>Runs on uniprocessors, parallel computers, and workstation networks. <item>Binary-, integer-, real-, and character-valued native data types. - <item>Full extensibility to support custom operators and new data types. - <item>Easy-to-use interface for novice and application users. - <item>Multiple levels of access for expert users. - <item>Parameterized population replacement. - <item>Multiple crossover, mutation, and selection operators. - <item>Easy integration of hill-climbing heuristics. - <item>Extensive debugging facilities. - <item>Large set of example problems. + <item>Full extensibility to support custom operators and new data types. + <item>Easy-to-use interface for novice and application users. + <item>Multiple levels of access for expert users. + <item>Parameterized population replacement. + <item>Multiple crossover, mutation, and selection operators. + <item>Easy integration of hill-climbing heuristics. + <item>Extensive debugging facilities. + <item>Large set of example problems. <item>Detailed users guide. </itemize> - + <label id="PIPE"> - <tag/PIPE/ + <tag/PIPE/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.idsia.ch/pub/rafal/" + <item>FTP site: <htmlurl + url="ftp://ftp.idsia.ch/pub/rafal/" name="ftp.idsia.ch/pub/rafal"> </itemize> - + Probabilistic Incremental Program Evolution (PIPE) is a novel - technique for automatic program synthesis. The software is written in C. + technique for automatic program synthesis. The software is written in C. It ... <itemize> @@ -2948,25 +2813,11 @@ LICENSE </itemize> - <label id="pygene"> - <tag/pygene/ - <itemize> - <item>Web site: <htmlurl - url="http://www.freenet.org.nz/python/pygene/" - name="www.freenet.org.nz/python/pygene/"> - </itemize> - - pygene is a simple and easily understandable library for genetic - algorithms and genetic programming in python. Includes examples - such as the travelling salesman problem. - - <label id="pygp"> <tag/pygp/ <itemize> - <item>Web site: <htmlurl - url="http://pygp.sourceforge.net/" - name="pygp.sourceforge.net/"> + <item>Web site: <htmlurl + url="http://sourceforge.net/projects/pygp/files/"> </itemize> Your basic genetic algorithm package for python. @@ -2975,7 +2826,7 @@ LICENSE <label id="tinygp"> <tag/tinygp/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.laserpirate.com/as3tinygp/"> </itemize> @@ -3068,7 +2919,6 @@ LICENSE priority scheduler; instead, at least, esep provides you with another choice to use a more intelligent scheduler, which carries out natural competition in an easy and effective way. - Xesep is a graphical user interface to the esep (Evolution Scheduling and Evolving Processes). It's intended to show users @@ -3081,40 +2931,22 @@ LICENSE <label id="Corewars"> <tag/Corewars/ <itemize> - <item>Web site: <htmlurl - url="http://corewars.sourceforge.net/" - name="corewars.sourceforge.net/"> <item>SourceForge site: <htmlurl - url="http://sourceforge.net/projects/corewars/" - name="sourceforge.net/projects/corewars/"> + url="http://sourceforge.net/projects/corewars/"> </itemize> - + Corewars is a game which simulates a virtual machine with a number of - programs. Each program tries to crash the others. The program that + programs. Each program tries to crash the others. The program that lasts the longest time wins. A number of sample programs are provided - and new programs can be written by the player. Screenshots are + and new programs can be written by the player. Screenshots are available at the Corewars homepage. - <label id="Grany-3"> - <tag/Grany-3/ - <itemize> - <item>Web site: <htmlurl - url="http://zarb.org/~gc/html/grany.html" - name="zarb.org/~gc/html/grany.html"> - </itemize> - - Grany-3 is a full-featured cellular automaton simulator, made in C++ - with Gtk--, flex++/bison++, doxygen and gettext, useful to granular - media physicists. - - <label id="JCASim"> <tag/JCASim/ <itemize> - <item>Web site: <htmlurl - url="http://www.jweimar.de/jcasim/" - name="www.jweimar.de/jcasim/"> + <item>Web site: <htmlurl + url="http://www.jweimar.de/jcasim/"> </itemize> JCASim is a general-purpose system for simulating cellular automata in @@ -3147,7 +2979,7 @@ LICENSE <sect>Alife & Complex Systems <label id="Alife & Complex Systems"> - <p> + <p> Alife takes yet another approach to exploring the mysteries of intelligence. It has many aspects similar to EC and Connectionism, but @@ -3163,14 +2995,13 @@ LICENSE just more general in definition (ie. alife is a type of complex system). Usually complex system software takes the form of a simulator. - + <sect1>Alife & CS class/code libraries - <p> + <p> These are libraries of code or classes for use in programming within the artificial life field. They are not meant as stand alone applications, but rather as tools for building your own applications. - <descrip> @@ -3179,27 +3010,25 @@ LICENSE <label id="AgentFarms"> <tag/AgentFarms/ <itemize> - <item>Web site: <htmlurl - url="http://www.agentfarms.net" - name="www.agentfarms.net"> + <item>Web site: <htmlurl + url="http://www.agentfarms.net"> </itemize> Agent Farms is a system for modelling and simulation of complex, - multi-agent based systems. The system can be used for: + multi-agent based systems. The system can be used for: <itemize> <item>Creating models of multi-agent systems <item>Interactive and distributed simulation <item>Observation and visualisation of the simulation <item>Population modification and migration </itemize> - + <label id="Biome"> <tag/Biome/ <itemize> - <item>Web site: <htmlurl - url="http://sourceforge.net/projects/biome/" - name="sourceforge.net/projects/biome/"> + <item>Web site: <htmlurl + url="http://sourceforge.net/projects/biome/"> </itemize> Biome is a C++ library aimed at individual-based/agent-based @@ -3208,15 +3037,14 @@ LICENSE oriented design. Currently there is an event based scheduling system, a C++ified Mersenne-Twister RNG, several general analysis classes, some Qt-based GUI classes, a very basic persistence/database framework (used - also for parameter storage) and many other small useful things. + also for parameter storage) and many other small useful things. <label id="CAGE"> <tag/CAGE/ <itemize> - <item>Web site: <htmlurl - url="http://www.alcyone.com/software/cage/" - name="www.alcyone.com/software/cage/"> + <item>Web site: <htmlurl + url="http://www.alcyone.com/software/cage/"> </itemize> CAGE is a fairy generic and complete cellular automaton simulation @@ -3240,11 +3068,11 @@ LICENSE distinguishing features of Cellang, include support for: <itemize> - <item>any number of dimensions; - <item>compile time specification of each dimensions size; + <item>any number of dimensions; + <item>compile time specification of each dimensions size; cell neighborhoods of any size (though bounded at compile time) - and shape; - <item>positional and time dependent neighborhoods; + and shape; + <item>positional and time dependent neighborhoods; <item>associating multiple values (fields), including arrays, with each cell; <item>associating a potentially unbounded number of mobile @@ -3281,27 +3109,10 @@ LICENSE mechanism - <label id="Jet's Neural Architecture"> - <tag/Jet's Neural Architecture/ - <itemize> - <item>Web site: <htmlurl - url="http://www.voltar-confed.org/jneural/" - name="www.voltar-confed.org/jneural/"> - </itemize> - - Jet's Neural Architecture is a C++ framework for doing neural net - projects. The goals of this project were to make a fast, flexible - neural architecture that isn't stuck to one kind of net and to make - sure that end users could easily write useful applications. All the - documentation is also easily readable. - - <label id="MAML"> <tag/MAML/ <itemize> - <item>Web site: <htmlurl - url="http://www.maml.hu/" - name="www.maml.hu"> + <item>Web site: <htmlurl url="http://www.maml.hu/"> </itemize> The current version of MAML is basically an extension to Objective-C @@ -3315,13 +3126,12 @@ LICENSE <label id="MASON"> <tag/MASON/ <itemize> - <item>Web site: <htmlurl - url="http://cs.gmu.edu/~eclab/projects/mason/" - name="cs.gmu.edu/~eclab/projects/mason/"> + <item>Web site: <htmlurl + url="http://cs.gmu.edu/~eclab/projects/mason/"> </itemize> MASON Stands for Multi-Agent Simulator Of Neighborhoods... or - Networks... or something... + Networks... or something... MASON is a fast discrete-event multi-agent simulation library core in Java, designed to be the foundation for large custom-purpose Java @@ -3333,14 +3143,11 @@ LICENSE <label id="SimWorld"> <tag/SimWorld/ <itemize> - <item>Web site: <htmlurl - url="http://www.nd.edu/~airolab/simworld/" - name="www.nd.edu/~airolab/simworld/"> - <item>New Web site?: <htmlurl - url="http://hri.cogs.indiana.edu/"> + <item>Web site: http://www.nd.edu/~airolab/simworld/ + <item>New Web site?: http://hrilab.tufts.edu/ </itemize> - SimWorld is a free artificial life simulation (based on the free + SimWorld is a free artificial life simulation (based on the free <ref id="SimAgent"> toolkit developed by Aaron Sloman), which provides functionality for running different interacting agents and objects in a simulated, continuous environment. The agents are controlled by rules @@ -3351,11 +3158,11 @@ LICENSE <label id="Swarm"> <tag/Swarm/ <itemize> - <item>Web site: <htmlurl - url="http://www.swarm.org/wiki/Swarm_main_page" + <item>Web site: <htmlurl + url="http://www.swarm.org/wiki/Swarm_main_page" name="www.swarm.org/wiki/Swarm_main_page"> - <item>FTP site: <htmlurl - url="http://ftp.swarm.org/pub/swarm/" + <item>FTP site: <htmlurl + url="http://ftp.swarm.org/pub/swarm/" name="ftp.swarm.org/pub/swarm/"> </itemize> @@ -3387,35 +3194,14 @@ LICENSE <label id="Achilles"> <tag/Achilles/ <itemize> - <item>Web site: <htmlurl - url="http://achilles.sourceforge.net/" - name="achilles.sourceforge.net"> + <item>Web site: <htmlurl + url="http://achilles.sourceforge.net/"> </itemize> Achilles is an evolution simulation based on Larry Yaeger's PolyWorld. It uses Hebbian neural networks, and an extremely simplified physical model that allows virtual organisms to interact freely in a simulated - environment. - - - <label id="AntWars"> - <tag/AntWars/ - <itemize> - <item>Web site: <htmlurl - url="http://ant-wars.net/"> - </itemize> - - Ant Wars is a competition which pits clever programs against each - other to do battle and compete for food in virtual worlds. Each - contestant is a species of ant, which can visualize only the world - immediately around him and pheromones left by fellow and enemy ants. - Using this information, the ant brain (a simple state machine) must - guide the ant towards collecting food at his home ant hill, while - fending off or attacking enemies. - - Clever use of pheromones and subtle behaviors can create large scale - tactics such as raiding, defense, harvesting, and scouting when many - ants cooperate. + environment. <label id="Avida"> @@ -3468,27 +3254,24 @@ LICENSE simulate realistic creatures, and an OpenGL display engine so you can visualize your simulated worlds. - + <label id="BugsX"> <tag/BugsX/ <itemize> <item>FTP site: <htmlurl - url="http://surf.de.uu.net/zooland/download/packages/bugsx/" - name="http://surf.de.uu.net/zooland/download/packages/bugsx/"> + url="https://github.com/porridge/bugsx"> </itemize> - Display and evolve biomorphs. It is a program which draws the biomorphs based on parametric plots of Fourier sine and cosine series and let's you play with them using the genetic algorithm. - + <label id="Creatures Docking Station"> <tag/Creatures Docking Station/ <itemize> - <item>Linux info: <htmlurl - url="http://sylv.inkwell.com.ru/" - name="sylv.inkwell.com.ru"> + <item>Linux info: <htmlurl + url="http://www.creaturesdockingstation.com/"> </itemize> This is a free version of the Creatures3 ALife game. It has fewer @@ -3499,7 +3282,7 @@ LICENSE pretty nice balance between fun and science, or so I'm told. (summary written by Steve Grand included below) - + The eponymous creatures in this computer game are called Norns, and the world's population of them at one stage hovered around the five million mark, making them more common than many familiar natural species. Each @@ -3545,7 +3328,7 @@ LICENSE <label id="dblife-dblifelib"> <tag/dblife & dblifelib/ <itemize> - <item>FTP site: <htmlurl + <item>FTP site: <htmlurl url="http://ibiblio.org/pub/Linux/science/ai/life/" name="ibiblio.org/pub/Linux/science/ai/life/"> </itemize> @@ -3555,12 +3338,12 @@ LICENSE that:-). But it IS meant to allow the easy editing and viewing of Life objects and has some powerful features. The related dblifelib package is a library of Life objects to use with the program. - + <it>dblifelib:</it> This is a library of interesting Life objects, including oscillators, spaceships, puffers, and other weird things. The related dblife package contains a Life program which can read the objects in the Library. - + <label id="Drone"> <tag/Drone/ @@ -3579,26 +3362,24 @@ LICENSE was originally designed for use with the Swarm agent-based simulation framework, but Drone can be used with any simulation program that reads parameters from the command line or from an input file. - + <label id="EcoLab"> <tag/EcoLab/ <itemize> - <item>Web site: <htmlurl - url="http://parallel.hpc.unsw.edu.au/rks/ecolab/" - name="parallel.hpc.unsw.edu.au/rks/ecolab/"> + <item>Web site: <htmlurl url="http://ecolab.sourceforge.net/"> </itemize> - + EcoLab is a system that implements an abstract ecology model. It is written as a set of Tcl/Tk commands so that the model parameters can easily be changed on the fly by means of editing a script. The model itself is written in C++. - + <label id="Framsticks"> <tag/Framsticks/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.frams.alife.pl/"> </itemize> @@ -3614,10 +3395,8 @@ LICENSE <label id="Fluidiom"> <tag/Fluidiom/ <itemize> - <item>Web site: <htmlurl - url="http://sourceforge.net/projects/fluidiom/"> - <item>Web site: <htmlurl - url="http://fluidiom.v2.nl/"> + <item>Web site: <htmlurl + url="http://ostatic.com/fluidiom"> </itemize> Evolutionary based alife platform. Has a game like feel which makes it @@ -3626,31 +3405,31 @@ LICENSE It takes a minimalist approach to spatial structure to make a body, adds articulation in the form of muscles, and then lets evolution take over to see if these bodies can learn to walk, run, crawl, or slither - from one place to the other. + from one place to the other. <label id="Game Of Life"> - <tag/Game Of Life (GOL)/ + <tag/Game Of Life (GOL)/ <itemize> <item>FTP site: <htmlurl url="http://ibiblio.org/pub/Linux/science/ai/life/" name="ibiblio.org/pub/Linux/science/ai/life/"> </itemize> - + GOL is a simulator for conway's game of life (a simple cellular automata), and other simple rule sets. The emphasis here is on speed and scale, in other words you can setup large and fast - simulations. + simulations. <label id="gant"> <tag/gant/ <itemize> - <item>Web site: <htmlurl - url="http://gant.sourceforge.net/" + <item>Web site: <htmlurl + url="http://gant.sourceforge.net/" name="gant.sourceforge.net"> </itemize> - + This project is an ANSI C++ implementation of the Generalized Langton Ant, which lives on a torus. @@ -3696,9 +3475,8 @@ LICENSE <label id="Langton's Ant"> <tag/Langton's Ant/ <itemize> - <item>Web site: <htmlurl - url="http://www.theory.org/software/ant/" - name="www.theory.org/software/ant/"> + <item>Web site: <htmlurl + url="http://theory.org/software/ant/"> </itemize> Langton's Ant is an example of a finite-state cellular automata. The @@ -3710,7 +3488,6 @@ LICENSE pattern field you start it out on, it eventually builds a "road," which is a series of 117 steps that repeat indefinitely, each time leaving the ant displaced one pixel vertically and horizontally. - <label id="LEE"> @@ -3721,21 +3498,19 @@ LICENSE name="www.informatics.indiana.edu/fil/LEE/"> </itemize> - LEE (Latent Energy Environments) is both an Alife model and a software tool to be used for simulations within the framework of that model. We hope that LEE will help understand a broad range of issues in theoretical, behavioral, and evolutionary biology. The LEE tool described here consists of approximately 7,000 lines of C code and runs in both Unix and Macintosh platforms. - + <label id="MATREM"> <tag/MATREM/ <itemize> - <item>Web site: <htmlurl - url="http://www.phys.uu.nl/˜romans/" - name="www.phys.uu.nl/˜romans/"> + <item>Web site: <htmlurl + url="http://www.romansland.nl/matrem/"> </itemize> Matrem is a computer program that simulates life. It belongs to the @@ -3748,8 +3523,8 @@ LICENSE <label id="Nanopond"> <tag/Nanopond/ <itemize> - <item>Web site: <htmlurl - url="http://www.greythumb.org/wiki/Nanopond"> + <item>Web site: <htmlurl + url="http://adam.ierymenko.name/nanopond.shtml"> </itemize> Nanopond is a "corewar style" evolvable instruction set based virtual @@ -3766,7 +3541,7 @@ LICENSE <label id="Noble Ape"> <tag/Noble Ape/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.nobleape.com/sim/" name="www.nobleape.com/sim/"> </itemize> @@ -3789,10 +3564,8 @@ LICENSE <label id="Polyworld"> <tag/Polyworld/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://sourceforge.net/projects/polyworld"> - <item>Web site: <htmlurl - url="http://www.beanblossom.in.us/larryy/PolyWorld.html"> </itemize> PolyWorld is a computational ecology that I developed to explore issues @@ -3818,12 +3591,12 @@ LICENSE <label id="POSES++"> - <tag/POSES++/ + <tag/POSES++/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.gpc.de/e_poses.html"> </itemize> - + The POSES++ software tool supports the development and simulation of models. Regarding the simulation technique models are suitable reproductions of real or planned systems for their @@ -3835,12 +3608,12 @@ LICENSE discontinuous behaviour. Also continuous systems can mostly be handled like discrete systems e.g., by quantity discretion and batch processing. - + <label id="Tierra"> <tag/Tierra/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://life.ou.edu/tierra/"> </itemize> @@ -3884,13 +3657,11 @@ LICENSE <label id="XLIFE"> <tag/XLIFE/ - <itemize> - <item>FTP site: <htmlurl - url="http://surf.de.uu.net/zooland/download/packages/xlife/" - name="surf.de.uu.net/zooland/download/packages/xlife/"> - </itemize> + <itemize> + <item>FTP site: <htmlurl + url="http://linux.maruhn.com/sec/xlife.html"> + </itemize> - This program will evolve patterns for John Horton Conway's game of Life. It will also handle general cellular automata with the orthogonal neighborhood and up to 8 states (it's possible to recompile @@ -3898,16 +3669,15 @@ LICENSE sample patterns are provided for the 8-state automaton of E. F. Codd, the Wireworld automaton, and a whole class of `Prisoner's Dilemma' games. - - <label id="Xtoys"> - <tag/Xtoys/ + + <label id="Xtoys"> + <tag/Xtoys/ <itemize> - <item>Web site: <htmlurl - url="http://thy.phy.bnl.gov/www/xtoys/xtoys.html" - name="thy.phy.bnl.gov/www/xtoys/xtoys.html"> + <item>Web site: <htmlurl + url="http://thy.phy.bnl.gov/www/xtoys/xtoys.html"> </itemize> - + xtoys contains a set of cellular automata simulators for X windows. Programs included are: <itemize> @@ -3916,19 +3686,16 @@ LICENSE <item> xautomalab --- a totalistic cellular automaton simulator, <item> xsand --- for the Bak, Tang, Wiesenfeld sandpile model, <item> xwaves --- demonstrates three different wave equations, - <item> schrodinger --- play with the Scrodinger equation in an + <item> schrodinger --- play with the Scrodinger equation in an adjustable potential. </itemize> </descrip> - - - <sect>Agents & Robotics <label id="Agents & Robotics"> <label id="Agents"> - <p> + <p> Software brains for computers that do stuff. Everythin from fun and games to data mining to physical robotics. This is a great hobbiest @@ -3954,11 +3721,11 @@ LICENSE <label id="3APL"> <tag/3APL/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.cs.uu.nl/3apl/"> - <item>Wikipedia entry: <htmlurl + <item>Wikipedia entry: <htmlurl url="http://en.wikipedia.org/wiki/3APL"> - <item>Mobile version: <htmlurl + <item>Mobile version: <htmlurl url="http://www.cs.uu.nl/3apl-m/"> </itemize> @@ -3978,18 +3745,18 @@ LICENSE <item>FTP site: <htmlurl url="http://www.cpan.org/modules/by-category/23_Miscellaneous_Modules/Agent/"> </itemize> - + The Agent is a prototype for an Information Agent system. It is both platform and language independent, as it stores contained information in simple packed strings. It can be packed and shipped across any network with any format, as it freezes itself in its current state. - + <label id="agentTool"> <tag/agentTool/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://agenttool.cis.ksu.edu/"> </itemize> @@ -4082,7 +3849,9 @@ LICENSE <tag/Bee-gent/ <itemize> <item>Web site: <htmlurl - url="http://www2.toshiba.co.jp/beegent/index.htm"> + url="http://www.toshiba.co.jp/rdc/beegent/download/download.htm"> + <item>FAQ: <htmlurl + url="http://www.toshiba.co.jp/rdc/beegent/faq/faq.htm"> </itemize> Bee-gent is a new type of development framework in that it is a 100% @@ -4097,7 +3866,7 @@ LICENSE <label id="Bond"> <tag/Bond/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://bond.cs.ucf.edu/"> </itemize> @@ -4106,13 +3875,13 @@ LICENSE directory, persistence, monitoring and security. Bond allows to easily build multi agent, distributed applications. Another application of Bond will be a Virtual Laboratory supporting data annotation and - metacomputing. + metacomputing. <label id="Cougaar"> <tag/Cougaar/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.cougaar.org/"> </itemize> @@ -4130,10 +3899,8 @@ LICENSE <itemize> <item>Web site: <htmlurl url="http://agent.cs.dartmouth.edu/software/agent2.0/"> - <item>FTP site: <htmlurl - url="ftp://ftp.cs.dartmouth.edu/pub/agents/"> </itemize> - + A transportable agent is a program that can migrate from machine to machine in a heterogeneous network. The program chooses when and where to migrate. It can suspend its execution at an arbitrary point, @@ -4147,7 +3914,7 @@ LICENSE <label id="DIET Agents"> <tag/DIET Agents/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://diet-agents.sourceforge.net"> </itemize> @@ -4194,10 +3961,10 @@ LICENSE <label id="Hive"> <tag/Hive/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://hive.sourceforge.net/"> </itemize> - + Hive is a Java software platform for creating distributed applications. Using Hive, programmers can easily create systems that connect and use data from all over the Internet. At its heart, Hive is an environment @@ -4208,27 +3975,25 @@ LICENSE <label id="ICM"> <tag/ICM/ <itemize> - <item>Web site (bad link?): <htmlurl - url="http://www.nar.fujitsulabs.com/"> - <item>SourceForge site: <htmlurl + <item>SourceForge site: <htmlurl url="http://sourceforge.net/projects/networkagent/"> </itemize> The Inter-Agent Communication Model (ICM) is a communication mechanism that can be used for sending messages between agents in an asynchronous fashion. Its intended application area is as a transportation mechanism - for agent communication languages (ACLs), such as KQML and FIPA's ACL. + for agent communication languages (ACLs), such as KQML and FIPA's ACL. <label id="Jacomma"> <tag/Jacomma/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://jacomma.sourceforge.net/"> - <item>SourceForge site: <htmlurl + <item>SourceForge site: <htmlurl url="http://sourceforge.net/projects/jacomma/"> </itemize> - + Jacomma is an agent development platform/framework for developing distributed, mobile, and reactive information agents with heterogeneous communication capabilities, in Java and JPython. @@ -4445,31 +4210,31 @@ LICENSE intelligence and agent technologies. It executes recipes (sequences of actions) to perform tasks. It is easy to specify a new action using XML and to implement it using Python. Recipes can be built and debugged - using a graphical interface. + using a graphical interface. <label id="NeL"> <tag/NeL/ <itemize> - <item>Web site: <htmlurl - url="http://www.nevrax.org/" + <item>Web site: <htmlurl + url="http://www.nevrax.org/" name="www.nevrax.org"> </itemize> NeL is actually a game development library (for massive multi-player - games), but I'm including it here as it (will) include a fairly + games), but I'm including it here as it (will) include a fairly sizable AI library. Here's a blurb from the whitepaper: The purpose of the AI library is to provide a pragmatic approach to creating a distributed agents platform. Its focus is agents; individual entities that communicate regardless of location, using an - action-reaction model. + action-reaction model. <label id="OAA"> <tag/OAA/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.ai.sri.com/˜oaa/" name="www.ai.sri.com/˜oaa/"> </itemize> @@ -4479,7 +4244,7 @@ LICENSE tasks assigned by human or non-human participants in the community. Distributed cooperation and high-level communication are two ideas central to the foundation of the OAA. - + It defines an interagent communication language and supports multiple platforms and programming languages. @@ -4529,7 +4294,7 @@ LICENSE <label id="OpenSteer"> <tag/OpenSteer/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://opensteer.sourceforge.net/" name="opensteer.sourceforge.net"> </itemize> @@ -4544,7 +4309,7 @@ LICENSE <tag/ORTS/ <itemize> <item>Web site: <htmlurl - url="http://www.cs.ualberta.ca/~mburo/orts/"> + url="https://skatgame.net/mburo/orts/"> </itemize> ORTS is a programming environment for studying real-time AI problems @@ -4574,29 +4339,11 @@ LICENSE increasing performance. - <label id="OSCAR"> - <tag/OSCAR/ - <itemize> - <item>Web site: <htmlurl - url="http://oscarhome.soc-sci.arizona.edu/ftp/OSCAR-web-page/oscar.html" - name="oscarhome.soc-sci.arizona.edu/ftp/OSCAR-web-page/oscar.html"> - </itemize> - - The goal of the OSCAR project is the formulation of a general theory of - rationality and its implementation in an artificial rational agent. The - function of artificial agents is to draw conclusions and make decisions - on the basis of information supplied to them. OSCAR is a fully - implemented architecture for rational agents, based upon a general - purpose defeasible reasoner. OSCAR is written in Common Lisp and is - free for educational and research purposes. - - <label id="Penguin!"> <tag/Penguin!/ <itemize> - <item>FTP site: <htmlurl - url="http://www.cpan.org/modules/by-category/23_Miscellaneous_Modules/Penguin/FSG/" - name="http://www.cpan.org/modules/by-category/23_Miscellaneous_Modules/Penguin/FSG/"> + <item>FTP site: <htmlurl + url="http://www.cpan.org/modules/by-category/23_Miscellaneous_Modules/Penguin/FSG/"> </itemize> Penguin is a Perl 5 module. It provides you with a set of functions which @@ -4824,7 +4571,7 @@ name="www.csee.umbc.edu/tkqml/"> url="http://www.marcush.net/IRS/" name="http://www.marcush.net/IRS/"> </itemize> - + UMPRS supports top-down, goal-based reasoning and selects goals and plans based on maximal priority. Execution of multiple simultaneous goals are supported, with suspension and resumption capabilities for @@ -4836,27 +4583,6 @@ name="www.csee.umbc.edu/tkqml/"> primitive function definition. - <label id="ViSe"> - <tag/Virtual Secretary Project (ViSe)/ (Tcl/Tk) - <itemize> - <item>Web site: <htmlurl - url="http://www.vise.cs.uit.no/vise/" - name="www.vise.cs.uit.no/vise/"> - </itemize> - - The motivation of the Virtual Secretary project is to construct - user-model-based intelligent software agents, which could in - most cases replace human for secretarial tasks, based on modern - mobile computing and computer network. The project includes two - different phases: the first phase (ViSe1) focuses on information - filtering and process migration, its goal is to create a secure - environment for software agents using the concept of user - models; the second phase (ViSe2) concentrates on agents' - intelligent and efficient cooperation in a distributed - environment, its goal is to construct cooperative agents for - achieving high intelligence. (Implemented in Tcl/TclX/Tix/Tk) - - <label id="WebMate"> <tag/WebMate/ <itemize> @@ -4894,29 +4620,10 @@ name="www.csee.umbc.edu/tkqml/"> </itemize> - - <label id="Zeus"> - <tag/Zeus/ - <itemize> - <item>Web site: <htmlurl - url="http://more.btexact.com/projects/agents/zeus/" - name="more.btexact.com/projects/agents/zeus/"> - </itemize> - - The construction of multi-agent systems involves long development - times and requires solutions to some considerable technical - difficulties. This has motivated the development of the ZEUS - toolkit, which provides a library of software components and tools - that facilitate the rapid design, development and deployment of - agent system - - - </descrip> - - <sect1>Robotics and Simulators + <label id="Robotics and Simulators"> <p> @@ -4986,7 +4693,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="CLARAty"> <tag/CLARAty/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://claraty.jpl.nasa.gov/man/overview/"> </itemize> @@ -4995,19 +4702,19 @@ name="www.csee.umbc.edu/tkqml/"> multiple implementations of any given functionality. Examples of such capabilities include pose estimation, navigation, locomotion and planning. In addition to supporting multiple algorithms, it provides - adaptations to multiple robotic platforms. + adaptations to multiple robotic platforms. This is a public release of the some of the code used in the Mars rover projects at NASA. It is under a free for non-commercial use licence and consists of large number of modules and algorithms along with extensive - documentation. + documentation. <label id="GNU Robots"> <tag/GNU Robots/ <itemize> - <item>Web site: <htmlurl - url="http://www.gnu.org/software/robots/"> + <item>Web site: <htmlurl + url="http://www.gnu.org/software/robots/"> </itemize> GNU Robots is a game/diversion where you construct a program for a @@ -5021,8 +4728,10 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Infon Battle Arena"> <tag/Infon Battle Arena/ <itemize> - <item>Web site: <htmlurl - url="http://infon.dividuum.de/trac/wiki"> + <item>Web site: <htmlurl + url="http://infon.dividuum.de/"> + <item>Web site: <htmlurl + url="https://github.com/dividuum/infon"> </itemize> Infon Battle Arena is a networked multiplayer real-time programming @@ -5036,12 +4745,11 @@ name="www.csee.umbc.edu/tkqml/"> <tag/Khepera Simulator/ <itemize> <item>Web site: <htmlurl - url="http://diwww.epfl.ch/lami/team/michel/khep-sim/index.html" - name="diwww.epfl.ch/lami/team/michel/khep-sim/"> + url="http://diwww.epfl.ch/w3lami/team/michel/khep-sim/"> </itemize> Khepera Simulator is a public domain software package written by - <htmlurl url="http://diwww.epfl.ch/lami/team/michel/" name="Olivier + <htmlurl url="http://diwww.epfl.ch/w3lami/team/michel/" name="Olivier MICHEL"> during the preparation of his Ph.D. thesis, at the Laboratoire I3S, URA 1376 of CNRS and University of Nice-Sophia Antipolis, France. It allows to write your own controller for the mobile robot Khepera @@ -5050,7 +4758,7 @@ name="www.csee.umbc.edu/tkqml/"> a Khepera robot, it can drive the real robot using the same control algorithm. It is mainly oriented toward to researchers studying autonomous agents. - + <label id="MRPT"> <tag/MRPT/ @@ -5069,7 +4777,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Nero"> <tag/Nero/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.nerogame.org/"> </itemize> @@ -5092,7 +4800,9 @@ name="www.csee.umbc.edu/tkqml/"> <tag/Orca/ <itemize> <item>Web site: <htmlurl - url="http://orca-robotics.sourceforge.net/orca/"> + url="http://orca-robotics.sourceforge.net/"> + <item>Web site: <htmlurl + url="https://github.com/naderman/orca-robotics"> </itemize> Orca is an open-source framework for developing component-based robotic @@ -5105,9 +4815,9 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Player"> <tag/Player/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://playerstage.sourceforge.net/"> - <item>Player wiki: <htmlurl + <item>Player wiki: <htmlurl url="http://playerstage.sourceforge.net/wiki/Player"> </itemize> @@ -5127,14 +4837,14 @@ name="www.csee.umbc.edu/tkqml/"> url="http://realtimebattle.sourceforge.net/"> </itemize> - RealTimeBattle is a programming game, in which robots controlled by - programs are fighting each other. The goal is to destroy the enemies, - using the radar to examine the environment and the cannon to shoot. + RealTimeBattle is a programming game, in which robots controlled by + programs are fighting each other. The goal is to destroy the enemies, + using the radar to examine the environment and the cannon to shoot. <itemize> - <item>Game progresses in real time, with the robot programs + <item>Game progresses in real time, with the robot programs running as child processes to RealTimeBattle. - <item>The robots communicate with the main program using the + <item>The robots communicate with the main program using the standard input and output. <item>Robots can be constructed in almost any programming language. <item>Maximum number of robots can compete simultaneously. @@ -5145,15 +4855,14 @@ name="www.csee.umbc.edu/tkqml/"> <item>Highly configurable. </itemize> - + <label id="Robocode"> <tag/Robocode/ <itemize> - <item>Web site: <htmlurl - url="http://robocode.sourceforge.net/" - name="robocode.sourceforge.net"> + <item>Web site: <htmlurl + url="http://robocode.sourceforge.net/"> </itemize> - + A java based robot combat programming game. It provides a simple API and class framework. It is designed as a means of learning Java and is easy to start using while not constraining the programmer from more @@ -5164,7 +4873,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Robodeb"> <tag/Robodeb/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.transterpreter.org/robodeb/"> </itemize> @@ -5175,17 +4884,17 @@ name="www.csee.umbc.edu/tkqml/"> portable and flexible runtime for the language. This combination is critical, as it provides a principled interface to the Player/Stage API, a set of widely used libraries for controlling the Pioneer3 - robotics platform. + robotics platform. <label id="RobotFlow"> <tag/RobotFlow/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://robotflow.sourceforge.net/"> </itemize> - RobotFlow is a mobile robotics tookit based on the + RobotFlow is a mobile robotics tookit based on the <htmlurl url="http://flowdesigner.sourceforge.net" name="FlowDesigner"> project. FlowDesigner is a data-flow oriented architecture, similar to Simulink (Matlab) or Labview that is free (LGPL) and versatile. The @@ -5198,7 +4907,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="RoboTournament"> <tag/RoboTournament/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://robotournament.sourceforge.net/"> </itemize> @@ -5213,9 +4922,7 @@ name="www.csee.umbc.edu/tkqml/"> <tag/ROS/ <itemize> <item>Web site: <htmlurl - url="http://pr.willowgarage.com/wiki/ROS"> - <item>Web site: <htmlurl - url="http://ros.sourceforge.net/"> + url="http://www.ros.org/wiki/"> </itemize> ROS is an operating system for your robot. It provides the services you @@ -5229,7 +4936,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Simbad"> <tag/Simbad/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://simbad.sourceforge.net/"> </itemize> @@ -5244,18 +4951,16 @@ name="www.csee.umbc.edu/tkqml/"> Simbad enables programmers to write their own robot controller, modify the environment and use the available sensors. Don't think of it as a finite product but merely as an opened framework to test your own - ideas. + ideas. <label id="SimRobot"> <tag/SimRobot/ <itemize> <item>Web site: <htmlurl - url="http://www.informatik.uni-bremen.de/simrobot/" - name="www.informatik.uni-bremen.de/˜simrobot/"> - <item>FTP site: <htmlurl - url="ftp://ftp.uni-bremen.de/pub/ZKW/INFORM/simrobot/" - name="ftp.uni-bremen.de/pub/ZKW/INFORM/simrobot/"> + url="http://www.informatik.uni-bremen.de/simrobot/"> + <item>FTP site: <htmlurl + url="ftp://ftp.uni-bremen.de/pub/ZKW/INFORM/simrobot/"> </itemize> SimRobot is a program for simulation of sensor based robots in a @@ -5265,16 +4970,16 @@ name="www.csee.umbc.edu/tkqml/"> <item>Simulation of robot kinematics <item>Hierarchically built scene definition via a simple definition language - <item>Various sensors built in: camera, facette eye, distance + <item>Various sensors built in: camera, facette eye, distance measurement, light sensor, etc. <item>Objects defined as polyeders <item>Emitter abstractly defined; can be interpreted e.g. as light or sound <item>Camera images computed according to the raytracing or Z-buffer algorithms known from computer graphics - <item>Specific sensor/motor software interface for communicating + <item>Specific sensor/motor software interface for communicating with the simulation - <item>Texture mapping onto the object surfaces: bitmaps in various + <item>Texture mapping onto the object surfaces: bitmaps in various formats <item>Comprehensive visualization of the scene: wire frame w/o hidden lines, sensor and actor values @@ -5282,19 +4987,18 @@ name="www.csee.umbc.edu/tkqml/"> and operation in the environment <item>Collision detection <item>Extendability with user defined object types - <item>Possible socket communication to e.g. the Khoros image + <item>Possible socket communication to e.g. the Khoros image processing software </itemize> - + <label id="TclRobots"> <tag/TclRobots/ <itemize> - <item>Web site: <htmlurl - url="http://www.nyx.net/˜tpoindex/" - name="www.nyx.net/˜tpoindex/"> + <item>Web site: <htmlurl + url="http://www.nyx.net/˜tpoindex/"> </itemize> - + TclRobots is a programming game, similar to 'Core War'. To play TclRobots, you must write a Tcl program that controls a robot. The robot's mission is to survive a battle with other robots. Two, three, @@ -5317,8 +5021,8 @@ name="www.csee.umbc.edu/tkqml/"> <label id="URBI"> <tag/URBI/ <itemize> - <item>Web site: <htmlurl - url="http://www.urbiforge.com/"> + <item>Web site: <htmlurl + url="http://www.urbiforge.org/"> </itemize> URBI is a Universal Real-time Behavior Interface and gives you a simple @@ -5336,12 +5040,10 @@ name="www.csee.umbc.edu/tkqml/"> <label id="VWORLD"> <tag/VWORLD/ <itemize> - <item>Web site: <htmlurl - url="http://zhar.net/projects/vworld/" - name="zhar.net/projects/vworld/"> + <item>Web site: <htmlurl + url="http://zhar.net/projects/vworld/"> </itemize> - Vworld is a simulated environment for research with autonomous agents written in prolog. It is currently in something of an beta stage. It works well with SWI-prolog, but should work with @@ -5402,10 +5104,10 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Statistical & Machine Learning"> <p> - - All about getting machines to learn to do something rather than + + All about getting machines to learn to do something rather than explicitly programming to do it. Tends to deal with pattern matching - a lot and are heavily math and statistically based. Technically + a lot and are heavily math and statistically based. Technically <ref id="Connectionism"> falls under this category, but it is such a large sub-field I'm keeping it in a separate section. @@ -5438,15 +5140,15 @@ name="www.csee.umbc.edu/tkqml/"> url="http://complearn.org/"> </itemize> - CompLearn is a software system built to support compression-based - learning in a wide variety of applications. It provides this support in - the form of a library written in highly portable ANSI C that runs in - most modern computer environments with minimal confusion. It also - supplies a small suite of simple, composable command-line utilities as - simple applications that use this library. Together with other commonly - used machine-learning tools such as LibSVM and GraphViz, CompLearn - forms an attractive offering in machine-learning frameworks and - toolkits. + CompLearn is a software system built to support compression-based + learning in a wide variety of applications. It provides this support in + the form of a library written in highly portable ANSI C that runs in + most modern computer environments with minimal confusion. It also + supplies a small suite of simple, composable command-line utilities as + simple applications that use this library. Together with other commonly + used machine-learning tools such as LibSVM and GraphViz, CompLearn + forms an attractive offering in machine-learning frameworks and + toolkits. <label id="Elefant"> @@ -5456,21 +5158,21 @@ name="www.csee.umbc.edu/tkqml/"> url="http://elefant.developer.nicta.com.au/"> </itemize> - Elefant (Efficient Learning, Large-scale Inference, and Optimisation - Toolkit) is an open source library for machine learning licensed under - the Mozilla Public License (MPL). We develop an open source machine - learning toolkit which provides + Elefant (Efficient Learning, Large-scale Inference, and Optimisation + Toolkit) is an open source library for machine learning licensed under + the Mozilla Public License (MPL). We develop an open source machine + learning toolkit which provides <itemize> - <item>algorithms for machine learning utilising the power of - multi-core/multi-threaded processors/operating systems (Linux, - WIndows, Mac OS X), - <item>a graphical user interface for users who want to quickly - prototype machine learning experiments, - <item>tutorials to support learning about Statistical Machine - Learning (Statistical Machine Learning at The Australian National - University), and - <item>detailed and precise documentation for each of the above. + <item>algorithms for machine learning utilising the power of + multi-core/multi-threaded processors/operating systems (Linux, + WIndows, Mac OS X), + <item>a graphical user interface for users who want to quickly + prototype machine learning experiments, + <item>tutorials to support learning about Statistical Machine + Learning (Statistical Machine Learning at The Australian National + University), and + <item>detailed and precise documentation for each of the above. </itemize> @@ -5481,13 +5183,13 @@ name="www.csee.umbc.edu/tkqml/"> url="http://homepages.inf.ed.ac.uk/lzhang10/maxent_toolkit.html"> </itemize> - The Maximum Entropy Toolkit provides a set of tools and library for - constructing maximum entropy (maxent) model in either Python or C++. + The Maximum Entropy Toolkit provides a set of tools and library for + constructing maximum entropy (maxent) model in either Python or C++. - Maxent Entropy Model is a general purpose machine learning framework - that has proved to be highly expressive and powerful in statistical - natural language processing, statistical physics, computer vision and - many other fields. + Maxent Entropy Model is a general purpose machine learning framework + that has proved to be highly expressive and powerful in statistical + natural language processing, statistical physics, computer vision and + many other fields. <label id="Milk"> @@ -5496,7 +5198,7 @@ name="www.csee.umbc.edu/tkqml/"> <item>Web site: <htmlurl url="http://packages.python.org/milk/"> <item>Web site: <htmlurl - url="http://github.com/luispedro/milk"> + url="https://github.com/luispedro/milk"> </itemize> Milk is a machine learning toolkit in Python. It's focus is on @@ -5510,9 +5212,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="NLTK"> <tag/NLTK/ <itemize> - <item>Web site: <htmlurl - url="http://www.nltk.org/" - name="www.nltk.org"> + <item>Web site: <htmlurl url="http://nltk.org/"> </itemize> NLTK, the Natural Language Toolkit, is a suite of Python libraries and @@ -5537,14 +5237,14 @@ name="www.csee.umbc.edu/tkqml/"> url="http://code.google.com/p/peach/"> </itemize> - Peach is a pure-python module, based on SciPy and NumPy to implement - algorithms for computational intelligence and machine learning. Methods - implemented include, but are not limited to, artificial neural - networks, fuzzy logic, genetic algorithms, swarm intelligence and much - more. + Peach is a pure-python module, based on SciPy and NumPy to implement + algorithms for computational intelligence and machine learning. Methods + implemented include, but are not limited to, artificial neural + networks, fuzzy logic, genetic algorithms, swarm intelligence and much + more. - The aim of this library is primarily educational. Nonetheless, care was - taken to make the methods implemented also very efficient. + The aim of this library is primarily educational. Nonetheless, care was + taken to make the methods implemented also very efficient. <label id="pebl"> @@ -5560,12 +5260,12 @@ name="www.csee.umbc.edu/tkqml/"> <itemize> <item>Can learn with observational and interventional data - <item>Handles missing values and hidden variables using exact and - heuristic methods - <item>Provides several learning algorithms; makes creating new ones - simple - <item>Has facilities for transparent parallel execution using several - cluster/grid resources + <item>Handles missing values and hidden variables using exact and + heuristic methods + <item>Provides several learning algorithms; makes creating new ones + simple + <item>Has facilities for transparent parallel execution using several + cluster/grid resources <item>Calculates edge marginals and consensus networks <item>Presents results in a variety of formats </itemize> @@ -5578,19 +5278,19 @@ name="www.csee.umbc.edu/tkqml/"> url="http://pybrain.org/"> </itemize> - PyBrain is a modular Machine Learning Library for Python. It's goal is - to offer flexible, easy-to-use yet still powerful algorithms for - Machine Learning Tasks and a variety of predefined environments to test - and compare your algorithms. + PyBrain is a modular Machine Learning Library for Python. It's goal is + to offer flexible, easy-to-use yet still powerful algorithms for + Machine Learning Tasks and a variety of predefined environments to test + and compare your algorithms. - PyBrain contains algorithms for neural networks, for reinforcement - learning (and the combination of the two), for unsupervised learning, - and evolution. Since most of the current problems deal with continuous - state and action spaces, function approximators (like neural networks) - must be used to cope with the large dimensionality. Our library is - built around neural networks in the kernel and all of the training - methods accept a neural network as the to-be-trained instance. This - makes PyBrain a powerful tool for real-life tasks. + PyBrain contains algorithms for neural networks, for reinforcement + learning (and the combination of the two), for unsupervised learning, + and evolution. Since most of the current problems deal with continuous + state and action spaces, function approximators (like neural networks) + must be used to cope with the large dimensionality. Our library is + built around neural networks in the kernel and all of the training + methods accept a neural network as the to-be-trained instance. This + makes PyBrain a powerful tool for real-life tasks. <label id="MBT"> @@ -5616,7 +5316,7 @@ name="www.csee.umbc.edu/tkqml/"> url="http://seat.massey.ac.nz/personal/s.r.marsland/MLBook.html"> </itemize> - Not a library per-say, but a whole slew of example machine learning + Not a library per-say, but a whole slew of example machine learning algorithms from the book "Machine Learning: An Algorithmic Perspective" by Stephen Marsland. All code is written in python. @@ -5625,10 +5325,10 @@ name="www.csee.umbc.edu/tkqml/"> <tag/scikits.learn/ <itemize> <item>Web site: <htmlurl - url="http://scikit-learn.sourceforge.net/"> + url="http://scikit-learn.org/stable/"> </itemize> - scikits.learn is a Python module integrating classic machine learning + scikits-learn is a Python module integrating classic machine learning algorithms in the tightly-knit world of scientific Python packages (numpy, scipy, matplotlib). It aims to provide simple and efficient solutions to learning problems that are accessible to everybody and @@ -5636,6 +5336,41 @@ name="www.csee.umbc.edu/tkqml/"> science and engineering. + <label id="Shogun"> + <tag/Shogun/ + <itemize> + <item>Web site: <htmlurl + url="http://www.shogun-toolbox.org/"> + </itemize> + + The machine learning toolbox's focus is on large scale kernel methods + and especially on Support Vector Machines (SVM). It provides a generic + SVM object interfacing to several different SVM implementations, among + them the state of the art LibSVM and SVMLight. Each of the SVMs can be + combined with a variety of kernels. The toolbox not only provides + efficient implementations of the most common kernels, like the Linear, + Polynomial, Gaussian and Sigmoid Kernel but also comes with a number of + recent string kernels as e.g. the Locality Improved, Fischer, TOP, + Spectrum, Weighted Degree Kernel (with shifts). For the latter the + efficient LINADD optimizations are implemented. Also SHOGUN offers the + freedom of working with custom pre-computed kernels. One of its key + features is the combined kernel which can be constructed by a weighted + linear combination of a number of sub-kernels, each of which not + necessarily working on the same domain. An optimal sub-kernel weighting + can be learned using Multiple Kernel Learning. Currently SVM 2-class + classification and regression problems can be dealt with. However + SHOGUN also implements a number of linear methods like Linear + Discriminant Analysis (LDA), Linear Programming Machine (LPM), (Kernel) + Perceptrons and features algorithms to train hidden markov models. The + input feature-objects can be dense, sparse or strings and of type + int/short/double/char and can be converted into different feature + types. Chains of preprocessors (e.g. substracting the mean) can be + attached to each feature object allowing for on-the-fly pre-processing. + + SHOGUN is implemented in C++ and interfaces to Matlab(tm), R, Octave + and Python. + + <label id="timbl"> <tag/timbl/ <itemize> @@ -5691,6 +5426,21 @@ name="www.csee.umbc.edu/tkqml/"> principles. + <label id="Torch5"> + <tag/Torch5/ + <itemize> + <item>Web site: <htmlurl + url="http://torch5.sourceforge.net/"> + </itemize> + + Torch5 provides a matlab-like environment for state-of-the-art machine + learning algorithms. It is easy to use and provides a very efficient + implementation, thanks to a easy and fast scripting language (Lua) and + a underlying C++ implementation. It is distributed under a BSD license. + + This is the successor to the <ref id="Torch" name="Torch3"> project. + + <label id="Vowpal Wabbit"> <tag/Vowpal Wabbit/ <itemize> @@ -5717,15 +5467,15 @@ name="www.csee.umbc.edu/tkqml/"> <sect>Programming languages <label id="Programming languages"> <p> - + While any programming language can be used for artificial intelligence/life research, these are programming languages which are used extensively for, if not specifically made for, artificial - intelligence programming. + intelligence programming. <descrip> - + <label id="2APL"> <tag/2APL/ <itemize> @@ -5782,9 +5532,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Ciao Prolog"> <tag/Ciao Prolog/ <itemize> - <item>Web site: <htmlurl - url="http://www.clip.dia.fi.upm.es/Software/Ciao/" - name="www.clip.dia.fi.upm.es/Software/Ciao/"> + <item>Web site: <htmlurl url="http://www.ciaohome.org/"> </itemize> Ciao is a complete Prolog system subsuming ISO-Prolog with a novel @@ -5801,7 +5549,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Curry"> <tag/Curry/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.informatik.uni-kiel.de/~mh/curry/"> </itemize> @@ -5820,32 +5568,14 @@ name="www.csee.umbc.edu/tkqml/"> provides additional features in comparison to the pure languages (compared to functional programming: search, computing with partial information; compared to logic programming: more efficient evaluation - due to the deterministic and demand-driven evaluation of functions). - - - <label id="DHARMI"> - <tag/DHARMI/ - <itemize> - <item>Web site: <htmlurl - url="http://megazone.bigpanda.com/˜wolf/DHARMI/" - name="http://megazone.bigpanda.com/˜wolf/DHARMI/"> - </itemize> - - DHARMI is a high level spatial, tinker-toy like language who's - components are transparently administered by a background - process called the Habitat. As the name suggests, the language - was designed to make modelling prototypes and handle living - data. Programs can be modified while running. This is accomplished - by blurring the distinction between source code, program, - and data. + due to the deterministic and demand-driven evaluation of functions). <label id="ECLiPSe"> <tag/ECLiPSe/ <itemize> - <item>Web site: <htmlurl - url="http://eclipse.crosscoreop.com/eclipse/" - name="eclipse.crosscoreop.com/eclipse/"> + <item>Web site: <htmlurl + url="http://eclipseclp.org/"> </itemize> ECLiPSe is a software system for the cost-effective development and @@ -5862,10 +5592,10 @@ name="www.csee.umbc.edu/tkqml/"> <label id="ECoLisp"> <tag/ECoLisp/ <itemize> - <item>Web site (???): <htmlurl url="http://www.di.unipi.it/˜attardi/software.html" name="www.di.unipi.it/˜attardi/software.html"> + <item>Web site (???): <htmlurl + url="http://www.di.unipi.it/˜attardi/software.html"> </itemize> - ECoLisp (Embeddable Common Lisp) is an implementation of Common Lisp designed for being embeddable into C based applications. ECL uses standard C calling conventions for Lisp @@ -5889,55 +5619,52 @@ name="www.csee.umbc.edu/tkqml/"> <label id="ESTEREL"> <tag/ESTEREL/ <itemize> - <item>Web site: <htmlurl - url="http://www-sop.inria.fr/meije/esterel/" - name="www-sop.inria.fr/meije/esterel/"> + <item>Web site: <htmlurl + url="http://www-sop.inria.fr/meije/esterel/"> </itemize> - + Esterel is both a programming language, dedicated to programming reactive systems, and a compiler which translates Esterel programs into finite-state machines. It is particularly well-suited to programming reactive systems, including real-time systems and control automata. - + Only the binary is available for the language compiler. :P - + <label id="Godel"> <tag/Gödel/ <itemize> - <item>Web page: <htmlurl url="http://www.cs.bris.ac.uk/˜bowers/goedel.html" name="www.cs.bris.ac.uk/˜bowers/goedel.html"> + <item>Web page: <htmlurl + url="http://www.cs.bris.ac.uk/˜bowers/goedel.html"> </itemize> - - Gödel is a declarative, general-purpose programming language - in the family of logic programming languages. It is a strongly typed - language, the type system being based on many-sorted logic with - parametric polymorphism. It has a module system. Gödel supports - infinite precision integers, infinite precision rationals, and also - floating-point numbers. It can solve constraints over finite domains - of integers and also linear rational constraints. It supports - processing of finite sets. It also has a flexible computation rule - and a pruning operator which generalizes the commit of the concurrent - logic programming languages. Considerable emphasis is placed on - Gödel's meta- logical facilities which provide significant - support for meta-programs that do analysis, transformation, - compilation, verification, debugging, and so on. - - + + Gödel is a declarative, general-purpose programming language in the + family of logic programming languages. It is a strongly typed language, + the type system being based on many-sorted logic with parametric + polymorphism. It has a module system. Gödel supports infinite + precision integers, infinite precision rationals, and also + floating-point numbers. It can solve constraints over finite domains of + integers and also linear rational constraints. It supports processing of + finite sets. It also has a flexible computation rule and a pruning + operator which generalizes the commit of the concurrent logic + programming languages. Considerable emphasis is placed on Gödel's + meta- logical facilities which provide significant support for + meta-programs that do analysis, transformation, compilation, + verification, debugging, and so on. + + <label id="CLisp"> <tag/CLisp (Lisp)/ <itemize> <item>Web page: <htmlurl - url="http://clisp.sourceforge.net/" - name="clisp.sourceforge.net"> - <item>Alt Web site: <htmlurl - url="http://clisp.cons.org/" - name="clisp.cons.org"> + url="http://clisp.sourceforge.net/"> + <item>Alt Web site: <htmlurl url="http://clisp.org/"> </itemize> - + CLISP is a Common Lisp implementation by Bruno Haible and Michael - Stoll. It mostly supports the Lisp described by + Stoll. It mostly supports the Lisp described by <htmlurl - url="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/html/cltl/cltl2.html" + url="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/html/cltl/cltl2.html" name="Common LISP: The Language (2nd edition)"> and the ANSI Common Lisp standard. CLISP includes an interpreter, a byte-compiler, a large @@ -5947,34 +5674,30 @@ name="www.csee.umbc.edu/tkqml/"> The user interface language (English, German, French) is chosen at run time. Major packages that run in CLISP include CLX & Garnet. CLISP needs only 2 MB of memory. - - + + <label id="CMU CL"> <tag/CMU Common Lisp/ <itemize> - <item>Web page: <htmlurl - url="http://www.cons.org/cmucl/" - name="www.cons.org/cmucl/"> - <item>Linux Installation: <htmlurl - url="http://www.telent.net/lisp/howto.html" - name="www.telent.net/lisp/howto.html"> + <item>Web page: <htmlurl + url="http://www.cons.org/cmucl/"> + <item>Linux Installation: <htmlurl + url="http://www.telent.net/lisp/howto.html"> </itemize> - CMU Common Lisp is a public domain "industrial strength" Common Lisp programming environment. Many of the X3j13 changes have been incorporated into CMU CL. Wherever possible, this has been done so as to transparently allow the use of either CLtL1 or proposed ANSI CL. Probably the new features most interesting to users are SETF functions, LOOP and the WITH-COMPILATION-UNIT macro. - - + + <label id="Gnu-CL"> <tag/GCL (Lisp)/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.ma.utexas.edu/pub/gcl/" - name="ftp.ma.utexas.edu/pub/gcl/"> + <item>FTP site: <htmlurl + url="ftp://ftp.ma.utexas.edu/pub/gcl/"> </itemize> GNU Common Lisp (GCL) has a compiler and interpreter for Common @@ -5989,26 +5712,19 @@ name="www.csee.umbc.edu/tkqml/"> is maximally efficient on such calls. It has a conservative garbage collector which allows great freedom for the C compiler to put Lisp values in arbitrary registers. - It has a source level Lisp debugger for interpreted code, with display of source code in an Emacs window. Its profiling tools (based on the C profiling tools) count function calls and the time spent in each - function. - + function. + <label id="GNU Prolog"> <tag/GNU Prolog/ - <itemize> - <item>Web site: <htmlurl - url="http://gnu-prolog.inria.fr/" - name="gnu-prolog.inria.fr"> - <item>Web site: <htmlurl - url="http://pauillac.inria.fr/˜diaz/gnu-prolog/" - name="pauillac.inria.fr/˜diaz/gnu-prolog/"> + <itemize> + <item>Web site: <htmlurl url="http://www.gprolog.org/"> </itemize> - GNU Prolog is a free Prolog compiler with constraint solving over finite domains developed by Daniel Diaz. @@ -6017,14 +5733,14 @@ name="www.csee.umbc.edu/tkqml/"> then stand-alone. The size of this executable can be quite small since GNU Prolog can avoid to link the code of most unused built-in predicates. The performances of GNU Prolog are very encouraging - (comparable to commercial systems). + (comparable to commercial systems). Beside the native-code compilation, GNU Prolog offers a classical interactive interpreter (top-level) with a debugger. The Prolog part conforms to the ISO standard for Prolog with many extensions very useful in practice (global variables, OS interface, - sockets,...). + sockets,...). GNU Prolog also includes an efficient constraint solver over Finite Domains (FD). This opens contraint logic pogramming to the user @@ -6032,30 +5748,13 @@ name="www.csee.umbc.edu/tkqml/"> logic programming. - <label id="IBAL"> - <tag/IBAL/ - <itemize> - <item>Web site: <htmlurl - url="http://www.eecs.harvard.edu/˜avi/IBAL/" - name="www.eecs.harvard.edu/˜avi/IBAL/"> - </itemize> - - IBAL (pronounced "eyeball") is a general-purpose language for - probabilistic modeling, parameter estimation and decision making. It - generalizes Bayesian networks, hidden Markov models, stochastic context - free grammars, Markov decision processes, and allows many new - possibilities. It also provides a convenient programming-language - framework with libraries, automatic type checking and so on. - - <label id="lush"> <tag/lush/ <itemize> - <item>Web site: <htmlurl - url="http://lush.sourceforge.net/" - name="lush.sourceforge.net"> + <item>Web site: <htmlurl + url="http://lush.sourceforge.net/"> </itemize> - + Lush is an object-oriented programming language designed for researchers, experimenters, and engineers interested in large-scale numerical and graphic applications. Lush is designed to be used in @@ -6063,14 +5762,13 @@ name="www.csee.umbc.edu/tkqml/"> high-level, weakly-typed interpreted language, with the efficiency of a strongly-typed, natively-compiled language, and with the easy integration of code written in C, C++, or other languages. - + <label id="Maude"> <tag/Maude/ <itemize> - <item>Web site: <htmlurl - url="http://maude.cs.uiuc.edu/" - name="maude.cs.uiuc.edu"> + <item>Web site: <htmlurl + url="http://maude.cs.uiuc.edu/"> </itemize> Maude is a high-performance reflective language and system supporting @@ -6078,14 +5776,14 @@ name="www.csee.umbc.edu/tkqml/"> wide range of applications. Maude has been influenced in important ways by the OBJ3 language, which can be regarded as an equational logic sublanguage. Besides supporting equational specification and - programming, Maude also supports rewriting logic computation. + programming, Maude also supports rewriting logic computation. <label id="Mercury"> <tag/Mercury/ <itemize> <item>Web page: <htmlurl - url="http://www.cs.mu.oz.au/research/mercury/"> + url="http://mercurylang.org/"> </itemize> Mercury is a new, purely declarative logic programming language. Like @@ -6096,14 +5794,14 @@ name="www.csee.umbc.edu/tkqml/"> Mercury is designed for the construction of large, reliable, efficient software systems by teams of programmers. As a consequence, programming in Mercury has a different flavor than programming in Prolog. - - + + <label id="Mozart"> <tag/Mozart/ <itemize> <item>Web page: <htmlurl url="http://www.mozart-oz.org/"> </itemize> - + The Mozart system provides state-of-the-art support in two areas: open distributed computing and constraint-based inference. Mozart implements Oz, a concurrent object-oriented language with dataflow @@ -6115,7 +5813,7 @@ name="www.csee.umbc.edu/tkqml/"> abilities. We have developed applications in scheduling and time-tabling, in placement and configuration, in natural language and knowledge representation, multi-agent systems and sophisticated - collaborative tools. + collaborative tools. <label id="SWI Prolog"> @@ -6124,21 +5822,20 @@ name="www.csee.umbc.edu/tkqml/"> <item>Web page: <htmlurl url="http://www.swi-prolog.org/"> </itemize> - + SWI is a free version of prolog in the Edinburgh Prolog family. It is licensed under the LGPL with many nice features for an AI researcher, such as; a large library of built-in predicates, a module system, garbage collection, a two-way interface with the C/C++ language, coroutines, multi-threading, multiple constraint library, the XPCE graphics toolkit, plus many more. - + <label id="Push"> <tag/Push/ <itemize> - <item>Web site: <htmlurl - url="http://hampshire.edu/lspector/push.html" - name="hampshire.edu/lspector/push.html"> + <item>Web site: <htmlurl + url="http://hampshire.edu/lspector/push.html"> </itemize> Push is a programming language intended primarily for use in @@ -6161,9 +5858,8 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Kali Scheme"> <tag/Kali Scheme/ <itemize> - <item>Web site: <htmlurl - url="http://community.schemewiki.org/kali-scheme/" - name="http://community.schemewiki.org/kali-scheme/"> + <item>Web site: <htmlurl + url="http://community.schemewiki.org/kali-scheme/"> </itemize> Kali Scheme is a distributed implementation of Scheme that @@ -6180,14 +5876,13 @@ name="www.csee.umbc.edu/tkqml/"> message-based distributed framework that allows any Scheme object (including code vectors) to be sent and received in a message. - + <label id="RScheme"> <tag/RScheme/ <itemize> - <item>Web site:<htmlurl - url="http://www.rscheme.org/" - name="www.rscheme.org"> + <item>Web site:<htmlurl + url="http://www.rscheme.org/"> </itemize> RScheme is an object-oriented, extended version of the Scheme @@ -6201,15 +5896,14 @@ name="www.csee.umbc.edu/tkqml/"> (default) bytecode code generation system, and only compiling your time-critical code to machine code. This allows a nice adjustment of space/time tradeoffs. (see web site for details) - + <label id="Scheme 48"> <tag/Scheme 48/ <itemize> - <item>Web site: <htmlurl - url="http://s48.org/"> + <item>Web site: <htmlurl url="http://s48.org/"> </itemize> - + Scheme 48 is a Scheme implementation based on a virtual machine architecture. Scheme 48 is designed to be straightforward, flexible, reliable, and fast. It should be easily portable to 32-bit @@ -6221,33 +5915,32 @@ name="www.csee.umbc.edu/tkqml/"> Scheme 48 implements and exploits an experimental module system loosely derived from Standard ML and Scheme Xerox. The development environment supports interactive changes to modules and interfaces. - + <label id="SCM"> - <tag>SCM (<bf>Scheme</bf>) + <tag>SCM (<bf>Scheme</bf>) <itemize> - <item>Web site: <htmlurl - url="http://www-swiss.ai.mit.edu/˜jaffer/SCM.html" - name="www-swiss.ai.mit.edu/˜jaffer/SCM.html"> + <item>Web site: <htmlurl + url="http://people.csail.mit.edu/jaffer/SCM.html"> </itemize> SCM conforms to the Revisedˆ4 Report on the Algorithmic Language Scheme and the IEEE P1178 specification. Scm is written in C. It uses the following utilities (all available at the ftp site). - <itemize> + <itemize> <item>SLIB (Standard Scheme Library) is a portable Scheme library which is intended to provide compatibility and utility functions for all standard Scheme implementations, including SCM, Chez, Elk, Gambit, MacScheme, MITScheme, scheme->C, Scheme48, T3.1, and VSCM, and is available as the file - slib2c0.tar.gz. Written by Aubrey Jaffer. + slib2c0.tar.gz. Written by Aubrey Jaffer. <item>JACAL is a symbolic math system written in Scheme, and is available as the file jacal1a7.tar.gz. - <item>Interfaces to standard libraries including REGEX string - regular expression matching and the CURSES screen management + <item>Interfaces to standard libraries including REGEX string + regular expression matching and the CURSES screen management package. - <item>Available add-on packages including an interactive debugger, - database, X-window graphics, BGI graphics, Motif, and + <item>Available add-on packages including an interactive debugger, + database, X-window graphics, BGI graphics, Motif, and Open-Windows packages. <item>A compiler (HOBBIT, available separately) and dynamic linking of compiled modules. @@ -6259,7 +5952,7 @@ name="www.csee.umbc.edu/tkqml/"> <itemize> <item>Web site: <htmlurl url="http://www.path.berkeley.edu/shift/"> </itemize> - + Shift is a programming language for describing dynamic networks of hybrid automata. Such systems consist of components which can be created, interconnected and destroyed @@ -6274,7 +5967,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="STELLA"> <tag/STELLA/ <itemize> - <item>Web site: <htmlurl + <item>Web site: <htmlurl url="http://www.isi.edu/isd/LOOM/Stella/"> </itemize> @@ -6299,83 +5992,96 @@ name="www.csee.umbc.edu/tkqml/"> <label id="YAP Prolog"> <tag/YAP Prolog/ <itemize> - <item>Web site: <htmlurl - url="http://www.ncc.up.pt/˜vsc/Yap/"> - <item>Sourceforge site: <htmlurl + <item>Web site: <htmlurl + url="http://www.dcc.fc.up.pt/˜vsc/Yap/"> + <item>Sourceforge site: <htmlurl url="http://sourceforge.net/projects/yap/"> </itemize> - - YAP is a high-performance Prolog compiler developed at + + YAP is a high-performance Prolog compiler developed at LIACC/Universidade do Porto. Its Prolog engine is based in the WAM (Warren Abstract Machine), with several optimizations for better performance. YAP follows the Edinburgh tradition, and is largely - compatible with DEC-10 Prolog, Quintus Prolog, and especially + compatible with DEC-10 Prolog, Quintus Prolog, and especially with C-Prolog. Work on the more recent version of YAP strives at several goals: - + <itemize> <item>Portability: The whole system is now written in C. YAP - compiles in popular 32 bit machines, such as Suns and + compiles in popular 32 bit machines, such as Suns and Linux PCs, and in a 64 bit machines, the Alphas running - OSF Unix and Linux. + OSF Unix and Linux. <item>Performance: We have optimised the emulator to obtain performance comparable to or better than well-known Prolog - systems. In fact, the current version of YAP performs + systems. In fact, the current version of YAP performs better than the original one, written in assembly language. - <item>Robustness: We have tested the system with a large array + <item>Robustness: We have tested the system with a large array of Prolog applications. <item>Extensibility: YAP was designed internally from the beginning to encapsulate manipulation of terms. These principles were used, for example, to implement a simple and powerful C-interface. The new version of YAP extends - these principles to accomodate extensions to the + these principles to accomodate extensions to the unification algorithm, that we believe will be useful to implement extensions such as constraint programming. <item>Completeness: YAP has for a long time provided most builtins expected from a Edinburgh Prolog implementation. - These include I/O functionality, data-base operations, + These include I/O functionality, data-base operations, and modules. Work on YAP aims now at being compatible with - the Prolog standard. + the Prolog standard. <item>Openess: We would like to make new development of YAP - open to the user community. + open to the user community. <item>Research: YAP has been a vehicle for research within and - outside our group. Currently research is going on on + outside our group. Currently research is going on on parallelisation and tabulation, and we have started work - to support constraint handling. + to support constraint handling. </itemize> </descrip> - - <sect>Missing & Dead <label id="Missing & Dead"> <p> - + This is my area for old or bad entries. The MIA section is for entires for which I no longer have a valid home page. If you have any information regarding where I can find these now please let me know. The Dead section - is for projects that seem dead. Moving them here allows me to keep my - the main sections clean while allowing for interested parties to + is for projects that seem dead. Moving them here allows me to keep my + the main sections clean while allowing for interested parties to correct me in which case I can just move it back. <sect1>MIA - Projects missing linkage. <p> <descrip> - + + <label id="AntWars"> + <tag/AntWars/ + <itemize> + <item>Web site: http://ant-wars.net/ + </itemize> + + Ant Wars is a competition which pits clever programs against each + other to do battle and compete for food in virtual worlds. Each + contestant is a species of ant, which can visualize only the world + immediately around him and pheromones left by fellow and enemy ants. + Using this information, the ant brain (a simple state machine) must + guide the ant towards collecting food at his home ant hill, while + fending off or attacking enemies. + + Clever use of pheromones and subtle behaviors can create large scale + tactics such as raiding, defense, harvesting, and scouting when many + ants cooperate. + + <label id="CASE"> <tag/CASE/ <itemize> - <item>Web site: <htmlurl - url="http://www.iu.hio.no/˜cell/" - name="www.iu.hio.no/˜cell/"> - <item>FTP site: <htmlurl - url="ftp://ftp.iu.hio.no/pub/" - name="ftp.iu.hio.no/pub/"> + <item>Web site: http://www.iu.hio.no/˜cell/ + <item>FTP site: ftp://ftp.iu.hio.no/pub/ </itemize> - + CASE (Cellular Automaton Simulation Environment) is a C++ toolkit for visualizing discrete models in two dimensions: so-called cellular automata. The aim of this project is to @@ -6395,14 +6101,12 @@ name="www.csee.umbc.edu/tkqml/"> interaction with syntax. This enables the user to get an idea of the range of possibilities of semantic construction, and also where there is real convergence between theories. - - + + <label id="CLIG"> <tag/CLIG/ <itemize> - <item>Web site: <htmlurl - url="http://www.ags.uni-sb.de/˜konrad/clig.html" - name="www.ags.uni-sb.de/˜konrad/clig.html"> + <item>Web site: http://www.ags.uni-sb.de/˜konrad/clig.html </itemize> CLIG is an interactive, extendible grapher for visualizing linguistic @@ -6412,14 +6116,12 @@ name="www.csee.umbc.edu/tkqml/"> designed both to be stand-alone and to be used as an add-on for linguistic applications which display their output in a graphical manner. - + <label id="Corewar VM"> <tag/Corewar VM/ <itemize> - <item>Web site: <htmlurl - url="http://www.jedi.claranet.fr/" - name="www.jedi.claranet.fr/"> + <item>Web site: http://www.jedi.claranet.fr/ </itemize> This is a virtual machine written in Java (so it is a virtual machine @@ -6428,31 +6130,42 @@ name="www.csee.umbc.edu/tkqml/"> <label id="DAI"> <tag/DAI/ - <itemize> - <item>Web site: <htmlurl - url="http://starship.python.net/crew/gandalf/DNET/AI/" - name="starship.python.net/crew/gandalf/DNET/AI/"> + <itemize> + <item>Web site: http://starship.python.net/crew/gandalf/DNET/AI/ </itemize> - + A library for the Python programming language that provides an - object oriented interface to the CLIPS expert system tool. It + object oriented interface to the CLIPS expert system tool. It includes an interface to COOL (CLIPS Object Oriented Language) that allows: <itemize> <item>Investigate COOL classes</item> - <item>Create and manipulate with COOL instances</item> - <item>Manipulate with COOL message-handler's</item> - <item>Manipulate with Modules</item> + <item>Create and manipulate with COOL instances</item> + <item>Manipulate with COOL message-handler's</item> + <item>Manipulate with Modules</item> </itemize> - + + + <label id="DHARMI"> + <tag/DHARMI/ + <itemize> + <item>Web site: http://megazone.bigpanda.com/˜wolf/DHARMI/ + </itemize> + + DHARMI is a high level spatial, tinker-toy like language who's + components are transparently administered by a background + process called the Habitat. As the name suggests, the language + was designed to make modelling prototypes and handle living + data. Programs can be modified while running. This is accomplished + by blurring the distinction between source code, program, + and data. + <label id="Dunce"> <tag/Dunce/ <itemize> - <item>Web site: <htmlurl - url="http://www.boswa.com/boswabits/" - name="www.boswa.com/boswabits/"> + <item>Web site: http://www.boswa.com/boswabits/ </itemize> - + Dunce is a simple chatterbot (conversational AI) and a language for programming such chatterbots. It uses a basic regex pattern matching and a semi-neural rule/response firing mechanism (with excitement/decay @@ -6464,13 +6177,10 @@ name="www.csee.umbc.edu/tkqml/"> <label id="EcoSim"> <tag/EcoSim/ <itemize> - <item>Web site: <htmlurl - url="http://www.offis.de/projekte/projekt.php?id=140" - name="www.offis.de/projekte/projekt.php?id=140"> + <item>Web site: http://www.offis.de/projekte/projekt.php?id=140 </itemize> - NOTE: the above web site has info on EcoSim but no code to download. - + NOTE: the above web site has info on EcoSim but no code to download. In EcoSim an ecosystem is described by all static and dynamic properties of the individuals involved in the system as well as time @@ -6485,9 +6195,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Evo"> <tag/Evo/ <itemize> - <item>Web site: <htmlurl - url="http://omicrongroup.org/evo/" - name="omicrongroup.org/evo/"> + <item>Web site: http://omicrongroup.org/evo/ </itemize> Evo is a software development framework that allows developers to build @@ -6498,108 +6206,244 @@ name="www.csee.umbc.edu/tkqml/"> they are more adapted to their environment. + <label id="Grany-3"> + <tag/Grany-3/ + <itemize> + <item>Web site: http://zarb.org/~gc/html/grany.html + </itemize> + + Grany-3 is a full-featured cellular automaton simulator, made in C++ + with Gtk--, flex++/bison++, doxygen and gettext, useful to granular + media physicists. + + + <label id="IBAL"> + <tag/IBAL/ + <itemize> + <item>Web site: http://www.eecs.harvard.edu/˜avi/IBAL/ + </itemize> + + IBAL (pronounced "eyeball") is a general-purpose language for + probabilistic modeling, parameter estimation and decision making. It + generalizes Bayesian networks, hidden Markov models, stochastic context + free grammars, Markov decision processes, and allows many new + possibilities. It also provides a convenient programming-language + framework with libraries, automatic type checking and so on. + + <label id="IDEAL"> <tag/IDEAL/ <itemize> - <item>Web site: <htmlurl - url="http://yoda.cis.temple.edu:8080/ideal/" - name="yoda.cis.temple.edu:8080/ideal/"> + <item>Web site: http://yoda.cis.temple.edu:8080/ideal/ </itemize> - - IDEAL is a test bed for work in influence diagrams and - Bayesian networks. It contains various inference algorithms - for belief networks and evaluation algorithms for influence - diagrams. It contains facilities for creating and editing - influence diagrams and belief networks. - IDEAL is written in pure Common Lisp and so it will run in - Common Lisp on any platform. The emphasis in writing IDEAL has - been on code clarity and providing high level programming - abstractions. It thus is very suitable for experimental - implementations which need or extend belief network - technology. + IDEAL is a test bed for work in influence diagrams and + Bayesian networks. It contains various inference algorithms + for belief networks and evaluation algorithms for influence + diagrams. It contains facilities for creating and editing + influence diagrams and belief networks. + + IDEAL is written in pure Common Lisp and so it will run in + Common Lisp on any platform. The emphasis in writing IDEAL has + been on code clarity and providing high level programming + abstractions. It thus is very suitable for experimental + implementations which need or extend belief network + technology. + + At the highest level, IDEAL can be used as a subroutine + library which provides belief network inference and influence + diagram evaluation as a package. The code is documented in a + detailed manual and so it is also possible to work at a lower + level on extensions of belief network methods. + + IDEAL comes with an optional graphic interface written in + CLIM. If your Common Lisp also has CLIM, you can run the + graphic interface. - At the highest level, IDEAL can be used as a subroutine - library which provides belief network inference and influence - diagram evaluation as a package. The code is documented in a - detailed manual and so it is also possible to work at a lower - level on extensions of belief network methods. - - IDEAL comes with an optional graphic interface written in - CLIM. If your Common Lisp also has CLIM, you can run the - graphic interface. - <label id="Illuminator"> <tag/Illuminator/ <itemize> - <item>Web site: <htmlurl - url="http://documents.cfar.umd.edu/resources/source/illuminator.html" - name="documents.cfar.umd.edu/resources/source/illuminator.html"> + <item>Web site: http://documents.cfar.umd.edu/resources/source/illuminator.html </itemize> - Illuminator is a toolset for developing OCR and Image - Understanding applications. Illuminator has two major parts: a - library for representing, storing and retrieving OCR - information, heretofore called dafslib, and an X-Windows "DAFS" - file viewer, called illum. Illuminator and DAFS lib were - designed to supplant existing OCR formats and become a standard - in the industry. They particularly are extensible to handle more - than just English. - - The features of this release: - <itemize> - <item>5 magnification levels for images</item> - <item>flagged characters and words</item> - <item>unicode support -- American, British, French, German, - Greek, Italian, MICR, Norwegian, Russian, Spanish, Swedish, - keyboards </item> - <item>reads DAFS, TIFF's, PDA's (image only)</item> - <item>save to DAFS, ASCII/UTF or Unicode</item> - <item>Entity Viewer - shows properties, character choices, - bounding boxes image fragment for a selected entity, change - type, change content, hierarchy mode</item> - </itemize> + Illuminator is a toolset for developing OCR and Image + Understanding applications. Illuminator has two major parts: a + library for representing, storing and retrieving OCR + information, heretofore called dafslib, and an X-Windows "DAFS" + file viewer, called illum. Illuminator and DAFS lib were + designed to supplant existing OCR formats and become a standard + in the industry. They particularly are extensible to handle more + than just English. + + The features of this release: + <itemize> + <item>5 magnification levels for images</item> + <item>flagged characters and words</item> + <item>unicode support -- American, British, French, German, + Greek, Italian, MICR, Norwegian, Russian, Spanish, Swedish, + keyboards </item> + <item>reads DAFS, TIFF's, PDA's (image only)</item> + <item>save to DAFS, ASCII/UTF or Unicode</item> + <item>Entity Viewer - shows properties, character choices, + bounding boxes image fragment for a selected entity, change + type, change content, hierarchy mode</item> + </itemize> + + + <label id="Jet's Neural Architecture"> + <tag/Jet's Neural Architecture/ + <itemize> + <item>Web site: http://www.voltar-confed.org/jneural/ + </itemize> + + Jet's Neural Architecture is a C++ framework for doing neural net + projects. The goals of this project were to make a fast, flexible + neural architecture that isn't stuck to one kind of net and to make + sure that end users could easily write useful applications. All the + documentation is also easily readable. + + + <label id="Neural Networks at your Fingertips"> + <tag/Neural Networks at your Fingertips/ + <itemize> + <item>Web site: http://www.neural-networks-at-your-fingertips.com/ + </itemize> + + A set of ANSI C packages that illustrate Adaline networks, + back-propagation, the Hopfield model, BAM, Boltzman, CPN, SOM, and + ART1. Coded in portable, self-contained ANSI C. With complete example + applications from a variety of well-known application domains. + + + <label id="Neureka ANS"> + <tag/Neureka ANS (nn/xnn)/ + <itemize> + <item>FTP site: ftp://ftp.ii.uib.no/pub/neureka/ + </itemize> + + nn is a high-level neural network specification language. The + current version is best suited for feed-forward nets, but + recurrent models can and have been implemented, e.g. Hopfield + nets, Jordan/Elman nets, etc. In nn, it is easy to change + network dynamics. The nn compiler can generate C code or + executable programs (so there must be a C compiler available), + with a powerful command line interface (but everything may also + be controlled via the graphical interface, xnn). It is possible + for the user to write C routines that can be called from inside + the nn specification, and to use the nn specification as a + function that is called from a C program. Please note that no + programming is necessary in order to use the network models that + come with the system (`netpack'). + + xnn is a graphical front end to networks generated by the nn + compiler, and to the compiler itself. The xnn graphical + interface is intuitive and easy to use for beginners, yet + powerful, with many possibilities for visualizing network data. + + NOTE: You have to run the install program that comes with this + to get the license key installed. It gets put (by default) in + /usr/lib. If you (like myself) want to install the package + somewhere other than in the /usr directory structure (the + install program gives you this option) you will have to set up + some environmental variables (NNLIBDIR & NNINCLUDEDIR are + required). You can read about these (and a few other optional + variables) in appendix A of the documentation (pg 113). + + + <label id="NEURObjects"> + <tag/NEURObjects/ + <itemize> + <item>Web site: http://www.disi.unige.it/person/ValentiniG/NEURObjects/ + </itemize> + + NEURObjects is a set of C++ library classes for neural networks + development. The main goal of the library consists in supporting + researchers and practitioners in developing new neural network methods + and applications, exploiting the potentialities of object-oriented + design and programming. NEURObjects provides also general purpose + applications for classification problems and can be used for fast + prototyping of inductive machine learning applications. + + + <label id="OSCAR"> + <tag/OSCAR/ + <itemize> + <item>Web site: http://oscarhome.soc-sci.arizona.edu/ftp/OSCAR-web-page/oscar.html + </itemize> + + The goal of the OSCAR project is the formulation of a general theory of + rationality and its implementation in an artificial rational agent. The + function of artificial agents is to draw conclusions and make decisions + on the basis of information supplied to them. OSCAR is a fully + implemented architecture for rational agents, based upon a general + purpose defeasible reasoner. OSCAR is written in Common Lisp and is + free for educational and research purposes. <label id="PAI"> <tag/PAI/ <itemize> - <item>Web site: <htmlurl - url="http://utenti.quipo.it/claudioscordino/pai.html" - name="utenti.quipo.it/claudioscordino/pai.html"> + <item>Web site: http://utenti.quipo.it/claudioscordino/pai.html </itemize> - + AI (Programmable Artificial Intelligence) is a program capable of - having a conversation in its mother tongue, English. Written in + having a conversation in its mother tongue, English. Written in C++. + <label id="pygene"> + <tag/pygene/ + <itemize> + <item>Web site: http://www.freenet.org.nz/python/pygene/ + </itemize> + + pygene is a simple and easily understandable library for genetic + algorithms and genetic programming in python. Includes examples + such as the travelling salesman problem. + + + <label id="PyIE"> + <tag/PyIE/ + <itemize> + <item>repo: https://www.dfwpython.org/repo/Projects/PyIE/ + </itemize> + + PyIE is a hypothesis based, agenda driven, object oriented inference + engine written in Python. Inferencing modes include back chaining, + opportunistic forward chaining and explicit forward chaining. The + first-class object base supports metaclasses, classes, objects and + multiple, dynamic inheritance. All objects are first class objects and + all attributes are slot values, i.e. data members attached to some + object. + + PyIE uses a TMS (truth maintenance system) for first level (condition + change) non-monotonic reasoning. User defined metaclasses are being + explored to support second level (belief change) non-monotonic + reasoning. + + <label id="Python ANN"> <tag/Simple Neural Net (in Python)/ <itemize> - <item>Web site: <htmlurl - url="http://www.amk.ca/python/unmaintained/" - name="http://www.amk.ca/python/unmaintained/"> + <item>Web site: http://www.amk.ca/python/unmaintained/ </itemize> - + Simple neural network code, which implements a class for 3-level networks (input, hidden, and output layers). The only learning rule implemented is simple backpropagation. No documentation (or even comments) at all, because this is simply code that I use to experiment with. Includes modules containing sample datasets from Carl G. Looney's NN book. Requires the Numeric - extensions. - + extensions. + <label id="Python Fuzzy Logic Module"> <tag/Python Fuzzy Logic Module/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.csh.rit.edu/pub/members/retrev/" - name="ftp://ftp.csh.rit.edu/pub/members/retrev/"> + <item>FTP site: ftp://ftp.csh.rit.edu/pub/members/retrev/ </itemize> - + A simple python module for fuzzy logic. The file is 'fuz.tar.gz' in this directory. The author plans to also write a simple genetic algorithm and a neural net library as well. Check the 00_index file in @@ -6609,14 +6453,12 @@ name="www.csee.umbc.edu/tkqml/"> <label id="QUANT1"> <tag/QUANT1/ <itemize> - <item>Web site: <htmlurl - url="http://linux.irk.ru/projects/QUANT/" - name="linux.irk.ru/projects/QUANT/"> + <item>Web site: http://linux.irk.ru/projects/QUANT/ </itemize> This project seems to have gone proprietary. The only trace I can find - via google is at <htmlurl - url="http://www.zurich.co.uk/strategicrisk/softwaresupport/Quant1.htm">. + via google is at + http://www.zurich.co.uk/strategicrisk/softwaresupport/Quant1.htm. QUANT/1 stands for type QUANTifier. It aims to be an alternative to Prolog-like (Resulutional-like) systems. Main features include a lack @@ -6639,11 +6481,9 @@ name="www.csee.umbc.edu/tkqml/"> <label id="SCNN"> <tag/SCNN/ <itemize> - <item>Web site: <htmlurl - url="http://www.uni-frankfurt.de/fb13/iap/e_ag_rt/SCNN/" - name="www.uni-frankfurt.de/fb13/iap/e_ag_rt/SCNN/"> + <item>Web site: http://www.uni-frankfurt.de/fb13/iap/e_ag_rt/SCNN/ </itemize> - + SCNN is an universal simulating system for Cellular Neural Networks (CNN). CNN are analog processing neural networks with regular and local interconnections, governed by a set of @@ -6655,30 +6495,47 @@ name="www.csee.umbc.edu/tkqml/"> <label id="SPI"> <tag/Symbolic Probabilistic Inference (SPI)/ <itemize> - <item>FTP site: <htmlurl - url="ftp://ftp.engr.orst.edu/pub/dambrosi/spi/" - name="ftp.engr.orst.edu/pub/dambrosi/spi/"> - <item>Paper (ijar-94.ps): <htmlurl - url="ftp://ftp.engr.orst.edu/pub/dambrosi/" - name="ftp.engr.orst.edu/pub/dambrosi/"> + <item>FTP site: ftp://ftp.engr.orst.edu/pub/dambrosi/spi/ + <item>Paper (ijar-94.ps): ftp://ftp.engr.orst.edu/pub/dambrosi/ </itemize> - - Contains Common Lisp function libraries to implement SPI type baysean + Contains Common Lisp function libraries to implement SPI type baysean nets. Documentation is very limited. - Features: + Features: <itemize> - Probabilities, Local Expression Language Utilities, Explanation, + Probabilities, Local Expression Language Utilities, Explanation, Dynamic Models, and a TCL/TK based GUI. </itemize> + <label id="SPRLIB-ANNLIB"> + <tag/SPRLIB/ANNLIB/ + <itemize> + <item>Web site: http://www.ph.tn.tudelft.nl/˜sprlib/ + </itemize> + + SPRLIB (Statistical Pattern Recognition Library) was developed + to support the easy construction and simulation of pattern + classifiers. It consist of a library of functions (written in C) + that can be called from your own program. Most of the well-known + classifiers are present (k-nn, Fisher, Parzen, ....), as well as + error estimation and dataset generation routines. + + ANNLIB (Artificial Neural Networks Library) is a neural network + simulation library based on the data architecture laid down by + SPRLIB. The library contains numerous functions for creating, + training and testing feed-forward networks. Training algorithms + include back-propagation, pseudo-Newton, Levenberg-Marquardt, + conjugate gradient descent, BFGS.... Furthermore, it is possible + - due to the datastructures' general applicability - to build + Kohonen maps and other more exotic network architectures using + the same data types. + + <label id="Sugal"> <tag/Sugal/ <itemize> - <item>Web site: <htmlurl - url="http://www.trajan-software.demon.co.uk/sugal.htm" - name="www.trajan-software.demon.co.uk/sugal.htm"> + <item>Web site: http://www.trajan-software.demon.co.uk/sugal.htm </itemize> Sugal [soo-gall] is the SUnderland Genetic ALgorithm system. @@ -6686,14 +6543,24 @@ name="www.csee.umbc.edu/tkqml/"> Algorithms on a common software platform. As such, Sugal supports a large number of variants of Genetic Algorithms, and has extensive features to support customization and extension. - + + + <label id="ThoughtTreasure"> + <tag/ThoughtTreasure/ + <itemize> + <item>Web site: http://www.signiform.com/tt/htm/tt.htm + </itemize> + + ThoughtTreasure is a project to create a database of commonsense rules + for use in any application. It consists of a database of a little over + 100K rules and a C API to integrate it with your applications. Python, + Perl, Java and TCL wrappers are already available. + <label id="TIN"> <tag/TIN/ <itemize> - <item>Web site: <htmlurl - url="http://www.jetlag.demon.nl/" - name="www.jetlag.demon.nl"></item> + <item>Web site: http://www.jetlag.demon.nl/ </itemize> This program simulates primitive life-forms, equipped with some @@ -6713,9 +6580,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Ummon"> <tag/Ummon/ <itemize> - <item>Web site: <htmlurl - url="http://www.spacetide.com/projects/ummon/" - name="www.spacetide.com/projects/ummon/"> + <item>Web site: http://www.spacetide.com/projects/ummon/ </itemize> Ummon is an advanced Open Source chatterbot. The main principle of the @@ -6725,7 +6590,39 @@ name="www.csee.umbc.edu/tkqml/"> with support for different, customizable personalities. - + <label id="ViSe"> + <tag/Virtual Secretary Project (ViSe)/ (Tcl/Tk) + <itemize> + <item>Web site: http://www.vise.cs.uit.no/vise/ + </itemize> + + The motivation of the Virtual Secretary project is to construct + user-model-based intelligent software agents, which could in + most cases replace human for secretarial tasks, based on modern + mobile computing and computer network. The project includes two + different phases: the first phase (ViSe1) focuses on information + filtering and process migration, its goal is to create a secure + environment for software agents using the concept of user + models; the second phase (ViSe2) concentrates on agents' + intelligent and efficient cooperation in a distributed + environment, its goal is to construct cooperative agents for + achieving high intelligence. (Implemented in Tcl/TclX/Tix/Tk) + + + <label id="Zeus"> + <tag/Zeus/ + <itemize> + <item>Web site: http://more.btexact.com/projects/agents/zeus/ + </itemize> + + The construction of multi-agent systems involves long development + times and requires solutions to some considerable technical + difficulties. This has motivated the development of the ZEUS + toolkit, which provides a library of software components and tools + that facilitate the rapid design, development and deployment of + agent system + + </descrip> @@ -6738,8 +6635,7 @@ name="www.csee.umbc.edu/tkqml/"> <label id="FIPA-OS"> <tag/FIPA-OS/ <itemize> - <item>Web site: <htmlurl - url="http://fipa-os.sourceforge.net/index.htm"> + <item>Web site: http://fipa-os.sourceforge.net/index.htm </itemize> FIPA-OS is an open source implementation of the mandatory elements @@ -6750,17 +6646,27 @@ name="www.csee.umbc.edu/tkqml/"> Platform agents. It is implemented in Java. + <label id="NuPIC"> + <tag/NuPIC/ + <itemize> + <item>Web site: http://www.numenta.com/ + </itemize> + + The Numenta Platform for Intelligent Computing (NuPIC) is built around + HTM networds (Hierarchical Temporal Memory). Based on Jeff Hawkins idea + as laid out in his On Intelligence book. NuPIC consists of the Numenta + Tools Framework and the Numenta Runtime Engine. + + Free for non-commercial use. + + <label id="PDKB"> <tag/PDKB/ <itemize> - <item>Web site: <htmlurl - url="http://lynx.eaze.net/˜pdkb/web/" - name="lynx.eaze.net/˜pdkb/web/"> - <item>SourceForge site: <htmlurl - url="http://sourceforge.net/projects/pdkb/" - name="sourceforge.net/projects/pdkb"> + <item>Web site: http://lynx.eaze.net/˜pdkb/web/ + <item>SourceForge site: http://sourceforge.net/projects/pdkb/ </itemize> - + Public Domain Knowledge Bank (PDKB) is an Artificial Intelligence Knowledge Bank of common sense rules and facts. It is based on the Cyc Upper Ontology and the MELD language. @@ -6769,13 +6675,11 @@ name="www.csee.umbc.edu/tkqml/"> <label id="RobocodeNG"> <tag/RobocodeNG/ <itemize> - <item>Web site: <htmlurl - url="http://robocodeng.sourceforge.net/" - name="robocodeng.sourceforge.net"> + <item>Web site: http://robocodeng.sourceforge.net/ </itemize> Merged together with original <ref id="Robocode"> as of version 1.1. - + Extension of Robocode, the battling bot AI programming game. Like its parent, it is written in Java and meant as a learning environment. @@ -6783,14 +6687,12 @@ name="www.csee.umbc.edu/tkqml/"> <label id="Sulawesi"> <tag/Sulawesi/ <itemize> - <item>Web site: <htmlurl - url="http://wearables.essex.ac.uk/sulawesi/" - name="wearables.essex.ac.uk/sulawesi/"> + <item>Web site: http://wearables.essex.ac.uk/sulawesi/ </itemize> - + A framework called Sulawesi has been designed and implemented to tackle what has been considered to be important challenges in a - wearable user interface. The ability to accept input from any + wearable user interface. The ability to accept input from any number of modalities, and perform if necessary a translation to any number of modal outputs. It does this primarily through a set of proactive agents to act on the input. @@ -6799,22 +6701,17 @@ name="www.csee.umbc.edu/tkqml/"> <label id="TresBel"> <tag/TresBel/ <itemize> - <item>Abstract: <htmlurl - url="http://iridia.ulb.ac.be/Projects/imple.html" - name="iridia.ulb.ac.be/Projects/imple.html"> - <item>Direct Download: <htmlurl - url="ftp://iridia.ulb.ac.be/pub/hongxu/software/TresBel.tar.Z" - name="ftp://iridia.ulb.ac.be/pub/hongxu/software/TresBel.tar.Z"> + <item>Abstract: http://iridia.ulb.ac.be/Projects/imple.html + <item>Direct Download: ftp://iridia.ulb.ac.be/pub/hongxu/software/TresBel.tar.Z </itemize> - + This project seems to have been superseded by <ref id="Pulcinella">. - Libraries containing (Allegro) Common Lisp code for Belief Functions - (aka. Dempster-Shafer evidential reasoning) as a representation + Libraries containing (Allegro) Common Lisp code for Belief Functions + (aka. Dempster-Shafer evidential reasoning) as a representation of uncertainty. Very little documentation. Has a limited GUI. - </descrip> </article>