Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
============================================================================================================ MILA will stop developing Theano: https://groups.google.com/d/msg/theano-users/7Poq8BZutbY/rNCIfvAEAwAJ
To install the package, see this page: http://deeplearning.net/software/theano/install.html
For the documentation, see the project website: http://deeplearning.net/software/theano/
Related Projects: https://github.com/Theano/Theano/wiki/Related-projects
It is recommended that you look at the documentation on the website, as it will be more current than the documentation included with the package.
In order to build the documentation yourself, you will need sphinx. Issue the following command:
Documentation is built into
The PDF of the documentation can be found at
Theano(current directory) is the distribution directory.
Theano/theanocontains the package
Theano/theanohas several submodules:
compileare the core
scalardepends upon core
sandboxcan depend on everything else
Theano/examplesare copies of the example found on the wiki
Theano/examplesare in the distribution, but not in the Python package
Theano/bincontains executable scripts that are copied to the bin folder when the Python package is installed
Tests are distributed and are part of the package, i.e. fall in the appropriate submodules
Theano/doccontains files and scripts used to generate the documentation
Theano/htmlis where the documentation will be generated