Theano: A Python framework for fast computation of mathematical expressions
By Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermüller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, A. Belikov, A. Belopolsky and 102 more. 2016
2,380 citations recorded by the source corpus.
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.
Subfields: Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Model Architectures
- Yoshua Bengio
- Kyunghyun Cho
- Aaron C. Courville
- Ruslan Salakhutdinov
- Quoc V. Le
- J. Urgen Schmidhuber
- Richard Socher
- Mohit Bansal
Citations in the corpus
- Neural Autoregressive Distribution Estimation (2016, positive): “Our implementation is done using Theano (Team et al., 2016).”
- Root Mean Square Layer Normalization (2019, methodology): “To test the efficiency of layer normalization across different implementations, we perform experiments with Tensorflow [1], PyTorch [20] and Theano [29].”
- The Reversible Residual Network: Backpropagation Without Storing Activations (2017, methodology): “Much of this work has focused on the modification of memory allocation within the training algorithms themselves [1, 2].”
- On the Quantitative Analysis of Decoder-Based Generative Models (2016, methodology): “We also thank the developers of Lasagne [2] and Theano [1].”
- Adversarially Learned Inference (2016, methodology): “We would also like to thank the developers of Theano (Bergstra et al., 2010; Bastien et al., 2012; Theano Development Team, 2016), Blocks and Fuel (van Merriënboer et al., 2015), which were used extensively for the paper.”