arXiv (Cornell University) · 2015 · 125 citations · 4 references
ComputingComputer ScienceArtificial IntelligenceData MiningMachine LearningDeep LearningGraph-based LearningNeural NetworksPattern RecognitionRepresentation LearningSupervised LearningBenchmark DatasetsConvolutional Neural Networks
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitates the training of complex neural network models by providing parametrized Theano operations, attaching metadata to Theano's symbolic computational graph, and providing an extensive set of utilities to assist training the networks, e.g. training algorithms, logging, monitoring, visualization, and serialization. Fuel provides a standard format for machine learning datasets. It allows the user to easily iterate over large datasets, performing many types of pre-processing on the fly.
4
Theano: new features and speed improvements
Frédéric Bastien, Pascal Lamblin, Razvan Pascanu et al. · arXiv (Cornell University) · 2012 · 1K citations · Full text
DRAW: A Recurrent Neural Network For Image Generation
Karol Gregor, Ivo Danihelka, Alex Graves et al. · arXiv (Cornell University) · 2015 · 965 citations · Full text
Pylearn2: a machine learning research library
Ian Goodfellow, David Warde-Farley, Pascal Lamblin et al. · arXiv (Cornell University) · 2013 · 193 citations · Full text