2012 · 209 citations · 4 references
ComputingComputer ScienceHigh-performance ComputingAlgorithmsMachine LearningProgramming LanguagesDeep LearningNeural NetworksOptimization For Machine LearningRepresentation LearningAutomatic DifferentiationDeep Learning AccelerationDeep Learning On GpusOptimization AlgorithmsSymbolic Differentiation
In this paper, we present Theano1, a framework in the Python programming language for defining, optimizing and evaluating expressions involving high-level operations on ten-sors. Theano offers most of NumPy’s functionality, but adds automatic symbolic differen-tiation, GPU support, and faster expression evaluation. Theano is a general mathematical tool, but it was developed with the goal of facilitating research in deep learning. The Deep Learning Tutorials2 introduce recent advances in deep learning, and showcase how Theano makes such algorithms compact, elegant, and fast.
4
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
A Fast Learning Algorithm for Deep Belief Nets
Geoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh · Neural Computation · 2006 · 16.4K citations
Extracting and composing robust features with denoising autoencoders
Pascal Vincent, Hugo Larochelle, Yoshua Bengio et al. · 2008 · 7.3K citations