Pylearn2 is a library designed to make machine learning research easy. Its a library based on Theano.

Highlights

Pylearn2 was used to set the state of the art on MNIST, CIFAR-10, CIFAR-100, and SVHN. See pylearn2.models.maxout or pylearn2/scripts/papers/maxout. Pylearn2 provides a wrapper around Alex Krizhevsky's extremely efficient GPU convolutional network library. This wrapper lets you use Theano's symbolic differentiation and other capabilities with minimal overhead. See pylearn2.sandbox.cuda_convnet.

Information

• Website: http://deeplearning.net/software/pylearn2
• GitHub: https://github.com/lisa-lab/pylearn2
• Documentation: http://deeplearning.net/software/pylearn2
• Community: http://groups.google.com/group/pylearn-users