Torch 7 : A Matlab-like Environment for Machine Learning

  title={Torch 7 : A Matlab-like Environment for Machine Learning},
  author={Ronan Collobert and Koray Kavukcuoglu and Cl{\'e}ment Farabet},
Torch7 is a versatile numeric computing framework and machine learning library that extends Lua. Its goal is to provide a flexible environment to design and train 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 easily be interfaced to third-party software thanks to Lua’s light interface. 
Highly Influential
This paper has highly influenced 90 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 1,384 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 862 extracted citations

1,384 Citations

Citations per Year
Semantic Scholar estimates that this publication has 1,384 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-3 of 3 references

Theano: a CPU and GPU math expression compiler

  • J. Bergstra, O. Breuleux, +5 authors Y. Bengio
  • In Proceedings of the Python for Scientific…
  • 2010
Highly Influential
3 Excerpts

Lush reference manual

  • Y. LeCun, L. Bottou
  • Technical report,
  • 2002
1 Excerpt

Sn: A simulator for connectionist models

  • L.-Y. Bottou, Y. LeCun
  • In Proceedings of NeuroNimes 88, Nimes,
  • 1988
1 Excerpt

Similar Papers

Loading similar papers…