Implementing Neural Networks Efficiently
Idiap Research Institute, Martigny, Switzerland
Springer, 2012
@techreport{muller2012implementing,
title={Implementing Neural Networks Efficiently},
author={M{"u}ller, K-R and Orr, Genevi{`e}ve and Montavon, Gr{‘e}goire and Collobert, Ronan and Farabet, Cl{‘e}ment and Kavukcuoglu, Koray},
year={2012},
institution={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.
December 29, 2013 by hgpu
