Pylearn2: a machine learning research library

Summary

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 are given.

Keywords

Flexibility (engineering), Extensibility, Computer science, Architecture, Order (exchange)

References

Note sur la convergence de méthodes de directions conjuguéesE. Polak, G. Ribière — 1969
The "independent components" of natural scenes are edge filters.Anthony J. Bell, Terrence J. Sejnowski — 1997
Deep Boltzmann MachinesRuslan Salakhutdinov, Geoffrey E. Hinton — 2009
Torch7: A Matlab-like Environment for Machine LearningRonan Collobert, Koray Kavukcuoglu, Clément Farabet — 2011
Estimation of Non-Normalized Statistical Models by Score MatchingAapo Hyvärinen — 2005
Theano: new features and speed improvementsFrédéric Bastien, Pascal Lamblin, Razvan Pascanu — 2012
Information processing in dynamical systems: foundations of harmony theoryPaul Smolensky — 1986
Improving neural networks by preventing co-adaptation of feature detectorsGeoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky — 2012
Computer-Intensive Methods in StatisticsPersi Diaconis, Bradley Efron — 1983
On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity ratesLaurent Younès — 1999
An empirical evaluation of deep architectures on problems with many factors of variationHugo Larochelle, Dumitru Erhan, Aaron Courville — 2007
THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMSRonald Aylmer Fisher — 1936
The collected papers of Peter J. W. DebyeGustaf Arrhenius — 1954
The Collected Papers of Peter J. W. Debye. Interscience, New York-London, 1954. xxi + 700 pp.Illus. $9.50Uwe Strauß — 1954
A Connection Between Score Matching and Denoising AutoencodersPascal Vincent — 2011
Auto-association by multilayer perceptrons and singular value decompositionH. Bourlard, Y. Kamp — 1988
Extracting and composing robust features with denoising autoencodersPascal Vincent, Hugo Larochelle, Yoshua Bengio — 2008
Acceleration of stochastic approximation by averagingB. T. Polyak, Anatoli Juditsky — 1992
Python for Scientific ComputingTravis E. Oliphant — 2007
Unsupervised and transfer learning challengeIsabelle Guyon, Gideon Dror, Vincent Lemaire — 2011

Cited by

Enhanced Higgs boson to τ(+)τ(-) search with deep learning.Pierre Baldi, Peter Sadowski, D. Whiteson — 2014
Understanding Locally Competitive NetworksRupesh K. Srivastava, Jonathan Masci, Faustino Gomez — 2014
Deep Learning of Affective Content from Audio for Computing Movie SimilaritiesIan Coots — 2015
Deep learning of representations and its application to computer visionIan Goodfellow — 2015
Feature Representation in Convolutional Neural NetworksBen Athiwaratkun, Keegan Kang — 2015
Computer Vision for Head Pose Estimation: Review of a CompetitionHeikki Huttunen, Ke Chen, Abhishek Thakur — 2015
Attention-Based Models for Speech RecognitionJan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk — 2015
An Improved Method for Predicting Linear B-cell Epitope Using Deep Maxout Networks.Yao Lian, Ze Chi Huang, Meng Ge — 2015
Deep Learning, Dark Knowledge, and Dark MatterPeter Sadowski, Julian Collado, D. Whiteson — 2014
Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methodsJascha Sohl‐Dickstein, Ben Poole, Surya Ganguli — 2013
Language Classes for Cloud Service Certification SystemsPhilipp Stephanow, Mark Gall — 2015
An Overview of Practical Applications of Protein Disorder Prediction and Drive for Faster, More Accurate PredictionsXin Deng, Jordan Gumm, Suman Karki — 2015
Soft-Deep Boltzmann MachinesTaichi Kiwaki — 2015
Unsupervised neural network based feature extraction using weak top-down constraintsHerman Kamper, Micha Elsner, Aren Jansen — 2015
Human arm pose modeling with learned features using joint convolutional neural networkChongguo Li, N.H.C. Yung, Xing Sun — 2015
An adaptive low dimensional quasi-Newton sum of functions optimizerJascha Sohl‐Dickstein, Ben Poole, Surya Ganguli — 2013
Real-time small obstacle detection on highways using compressive RBM road reconstructionClement Creusot, Asim Munawar — 2015
End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First ResultsJan Chorowski, Dzmitry Bahdanau, Kyunghyun Cho — 2014
Training deep neural networks with low precision multiplicationsMatthieu Courbariaux, Yoshua Bengio, Jean‐Pierre David — 2014
Resource-constrained classification using a cascade of neural network layersSam Leroux, Steven Bohez, Tim Verbelen — 2015

Related papers

Gradient-based learning applied to document recognitionYann LeCun, Léon Bottou, Yoshua Bengio — 1998
Improving neural networks by preventing co-adaptation of feature detectorsGeoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky — 2012
ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012
Theano: new features and speed improvementsFrédéric Bastien, Pascal Lamblin, Razvan Pascanu — 2012
Dropout: a simple way to prevent neural networks from overfittingNitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky — 2014
A Fast Learning Algorithm for Deep Belief NetsGeoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh — 2006
Learning Multiple Layers of Features from Tiny ImagesAlex Krizhevsky — 2024
Scikit-learn: Machine Learning in PythonFabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort — 2011
Learning Deep Architectures for AIYoshua Bengio — 2007
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsGeoffrey E. Hinton, Li Deng, Dong Yu — 2012