LDP
/
LDP
mirror of https://github.com/tLDP/LDP
0
1
Fork 0
Code Releases Activity

cleaned up Torch project entries

This commit is contained in:
jae 2013-06-06 18:10:45 +00:00
parent 5fbf038ce3
commit 11479780e6
1 changed files with 10 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
LDP/howto/linuxdoc/AI-Alife-HOWTO.sgml
View File

@ -874,42 +874,6 @@ United States.
offer you the right functionality.
<label id="Torch">
<tag/Torch/
<itemize>
<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.
<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.
</descrip>
@ -5470,19 +5434,19 @@ name="www.csee.umbc.edu/tkqml/">
principles.
<label id="Torch5">
<tag/Torch5/
<label id="Torch">
<tag/Torch/
<itemize>
<item>Web site: <htmlurl
url="http://torch5.sourceforge.net/">
<item>Web site: <htmlurl url="http://www.torch.ch/">
<item>Old versions:
<htmlurl url="http://torch5.sourceforge.net/" name="Torch5">
<htmlurl url="http://www.torch.ch/torch3/" name="Torch3">
</itemize>
Torch5 provides a matlab-like environment for state-of-the-art machine
Torch 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.
implementation, thanks to an easy and fast scripting language (Lua) and
a underlying C implementation.
<label id="Vowpal Wabbit">
@ -5497,7 +5461,7 @@ name="www.csee.umbc.edu/tkqml/">
<itemize>
<item>flexible input data specification
<item>speedy learning
<item>scalability (bounded memory footprint, suitable for
<item>scalability (bounded memory footprint, suitable for
distributed computation)
<item>feature pairing
</itemize>