Mercurial > pylearn

view doc/index.txt @ 1003:d19e3cb809c1

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Created online dataset, for testing PCD style learning algorithms. Image size is parametrizable, as well as the number of modes and their respective depth.
author gdesjardins
date Wed, 01 Sep 2010 17:58:43 -0400
parents 8837535006f1
children be53f56b37b8
line wrap: on
line source


Welcome
=======

Pylearn is a Python library for machine learning, built on top of Theano, our 
library for defining, optimizing and evaluating mathematical expressions
involving multi-dimensional arrays.

This documentation is under construction, but you can already access the
automatically-generated API doc, along with more extensive explanations for 
some modules.

Download
========

We recommend the latest development version, available via::

    hg clone http://hg.assembla.com/pylearn Pylearn

The ``pylearn`` subfolder should be on your ``$PYTHONPATH``.

Documentation
=============

For the moment, the following documentation is available.

* :doc:`io.SeriesTables module <seriestables>` -- Saves error series and other statistics during training
* `API <api/>`_ -- The automatically-generated API documentation

You can download the latest `PDF documentation <http://deeplearning.net/software/pylearn/pylearn.pdf>`_, rather than reading it online.