Pylearn2: a machine learning research library

By Ian J. Goodfellow, David Warde-Farley, Pascal Lamblin, Vincent Dumoulin, Mehdi Mirza, Razvan Pascanu, James Bergstra, Frédéric Bastien, Yoshua Bengio. 2013

305 citations recorded by the source corpus.

Pylearn2 is a machine learning research library. This does not just mean that it is a collection of machine learning algorithms that share a common API; it means that it has been designed for flexibility and extensibility in order to facilitate research projects that involve new or unusual use cases. In this paper we give a brief history of the library, an overview of its basic philosophy, a summary of the library's architecture, and a description of how the Pylearn2 community functions socially.

Subfields: Artificial Intelligence, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In ML Systems & Hardware

Citations in the corpus

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling (2014, background): “The authors would like to thank the developers of Theano [Bergstra et al., 2010, Bastien et al., 2012] and Pylearn2 [Goodfellow et al., 2013].”
FitNets: Hints for Thin Deep Nets (2014, methodology): “To validate our approach, we trained a teacher network of maxout convolutional layers as reported in Goodfellow et al. (2013b) and used the same FitNet architecture as in CIFAR-10.”
Theano: A Python framework for fast computation of mathematical expressions (2016, background): “For instance, machine learning and deep learning packages, such as Pylearn2 [8], Blocks [9], Lasagne [10], and Keras [11], have been developed with the goal of making it easier to express the architecture of deep learning models, and training algorithms, as mathematical expressions to be evaluated b”
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (2015, methodology): “We divided the images of each person into a training set (7 images) and a validation set (3 images), and trained each model using pylearn2’s stochastic gradient descent algorithm [15] until the model’s performance on the training set failed to improve after 100 iterations.”
Understanding Neural Networks Through Deep Visualization (2015, background): “We also note that tools that enable understanding will especially beneﬁt the vast numbers of newcomers to deep learning, who would like to take advantage of off-the-shelf software packages — like Theano (Bergstra et al., 2010), Pylearn2 (Goodfellow et al., 2013), Caffe (Jia et al., 2014), and Torch ”
An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks (2013, methodology): “Maxout (Goodfellow et al., 2013b): We trained each of these four activation functions with each of the two algorithms we considered, for a total of eight distinct methods.”