Torch 5 provides a matlab-like environment for state-of-the-art machine learning algorithms. It is easy to use and provides a very efficient implementation, thanks to a easy and fast scripting language (Lua) and a underlying C implementation.

Torch 5 is available at

Torch 5 is the official successor to Torch 3 (Ronan Collobert, Samy Bengio and Johnny Mariéthoz, IDIAP). Torch 3 is available at:

Collaborators:  Iain Melvin, Jason Weston, Ronan Collobert