Welcome to pySkyNet

pySkyNet is a python wrapper for SkyNet
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. Currently autoencoders are not implemented in pySkyNet
pySkyNet makes system calls to SkyNet and emulates the fit and predict user interface of sklearn.

Note

You need to have the mpi version of SkyNet installed for pySkyNet to work!
SkyNet is written by Philip Graff, Farhan Feroz, Michael P. Hobson, Anthony N. Lasenby