Theano: new features and speed improvements
Fr\'ed\'eric Bastien, Pascal Lamblin, Razvan Pascanu, James Bergstra,, Ian Goodfellow, Arnaud Bergeron, Nicolas Bouchard, David Warde-Farley, Yoshua, Bengio

TL;DR
This paper introduces new features and speed enhancements to Theano, a symbolic mathematics compiler, with benchmarks showing improved performance over Torch7 and RNNLM for machine learning tasks.
Contribution
The paper presents significant new features and efficiency improvements to Theano, along with benchmarking results comparing its performance to Torch7 and RNNLM.
Findings
Theano's performance is improved with new features.
Theano outperforms Torch7 in benchmarks.
Theano shows competitive results against RNNLM.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Model Reduction and Neural Networks · Numerical Methods and Algorithms
