English

Theano: new features and speed improvements

Symbolic Computation 2012-11-26 v1 Machine Learning

Abstract

Theano is a linear algebra compiler that optimizes a user's symbolically-specified mathematical computations to produce efficient low-level implementations. In this paper, we present new features and efficiency improvements to Theano, and benchmarks demonstrating Theano's performance relative to Torch7, a recently introduced machine learning library, and to RNNLM, a C++ library targeted at recurrent neural networks.

Keywords

Cite

@article{arxiv.1211.5590,
  title  = {Theano: new features and speed improvements},
  author = {Frédéric Bastien and Pascal Lamblin and Razvan Pascanu and James Bergstra and Ian Goodfellow and Arnaud Bergeron and Nicolas Bouchard and David Warde-Farley and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1211.5590},
  year   = {2012}
}

Comments

Presented at the Deep Learning Workshop, NIPS 2012

R2 v1 2026-06-21T22:43:21.684Z