http://pyskynet.readthedocs.org/en/latest/index.html
SkyNet is an efficient and robust neural network training code for machine learning. It is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SkyNet is implemented in C/C++ and fully parallelised using MPI.
SkyNet can de downloaded here: http://ccpforge.cse.rl.ac.uk/gf/project/skynet/
SkyNet is written by Philip Graff, Farhan Feroz, Michael P. Hobson, Anthony N. Lasenby http://xxx.lanl.gov/abs/1309.0790