view doc/index.txt @ 1133:9baa47482ccc

coding_style: Added a few more coding guidelines for compatibility with various Python versions
author Olivier Delalleau <delallea@iro>
date Wed, 15 Sep 2010 15:20:13 -0400
parents be53f56b37b8
children b699d096e6cc
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.

* `Formulas <formulas.html>`_ -- Built-in math formulas optimized for speed and robustness
* :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.