CHAPTER Collobert_SPRINGER_2012/IDIAP Implementing Neural Networks Efficiently Collobert, Ronan Kavukcuoglu, Koray Farabet, Clément Montavon, Grégoire Ed. Orr, Geneviève Ed. Müller, K. -R. Ed. machine-learning software EXTERNAL http://publications.idiap.ch/attachments/papers/2012/Collobert_SPRINGER_2012.pdf PUBLIC Neural Networks: Tricks of the Trade 2012 Springer Neural networks and machine learning algorithms in general require a flexible environment where new algorithm prototypes and experiments can be set up as quickly as possible with best possible computational performance. To that end, we provide a new framework called Torch7, that is especially suited to achieve both of these competing goals. Torch7 is a versatile numeric computing framework and machine learning library that extends a very lightweight and powerful programming language Lua. Its goal is to provide a flexible environment to design, train and deploy learning machines. Flexibility is obtained via Lua, an extremely lightweight scripting language. High performance is obtained via efficient OpenMP/SSE and CUDA implementations of low-level numeric routines. Torch7 can also easily be interfaced to third-party software thanks to Lua’s light C interface.