Pylearn2: a machine learning research library (2013-08-19T00:00:00.000000Z)

TL;DR

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.

Abstract

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.

Authors

Yoshua Bengio

69 papers

I. Goodfellow

19 papers

Razvan Pascanu

15 papers

TL;DR

Abstract

Authors

References56 items

Scaling Up Spike-and-Slab Models for Unsupervised Feature Learning

Challenges in representation learning: A report on three machine learning contests

Maxout Networks

Large Scale Distributed Deep Networks

ImageNet classification with deep convolutional neural networks

Theano: new features and speed improvements

Improving neural networks by preventing co-adaptation of feature detectors

Convolutional neural networks applied to house numbers digit classification

An Analysis of Single-Layer Networks in Unsupervised Feature Learning

Unsupervised and transfer learning challenge

Higher Order Contractive Auto-Encoder

A Connection Between Score Matching and Denoising Autoencoders

Large-Scale Learning of Embeddings with Reconstruction Sampling

Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Unsupervised Models of Images by Spikeand-Slab RBMs

A Spike and Slab Restricted Boltzmann Machine

Deep Sparse Rectifier Neural Networks

Scikit-learn: Machine Learning in Python

Noise-contrastive estimation: A new estimation principle for unnormalized statistical models

Nonlinear Learning using Local Coordinate Coding

Deep Boltzmann Machines

Invariant Object Recognition with Slow Feature Analysis

Training restricted Boltzmann machines using approximations to the likelihood gradient

Extracting and composing robust features with denoising autoencoders

An empirical evaluation of deep architectures on problems with many factors of variation

Python for Scientific Computing

Estimation of Non-Normalized Statistical Models by Score Matching

Rank, Trace-Norm and Max-Norm

Exponential Family Harmoniums with an Application to Information Retrieval

Learning methods for generic object recognition with invariance to pose and lighting

Training Products of Experts by Minimizing Contrastive Divergence

On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates

Convolutional networks for images, speech, and time series

The “independent components” of natural scenes are edge filters

Support-Vector Networks

Acceleration of stochastic approximation by averaging

Auto-association by multilayer perceptrons and singular value decomposition

Information processing in dynamical systems: foundations of harmony theory

Learning internal representations by error propagation

Computer-Intensive Methods in Statistics

The Collected Papers of Peter J. W. Debye. Interscience, New York-London, 1954. xxi + 700 pp.Illus. $9.50

The collected papers of Peter J. W. Debye

THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS

LIII. On lines and planes of closest fit to systems of points in space

Travis CI. http://travis-ci.org

Reading Digits in Natural Images with Unsupervised Feature Learning

Torch7: A Matlab-like Environment for Machine Learning

NIPS Workshop on Challenges in Learning Hierarchical Models: Transfer Learning and Optimization

The stair vision library

Theano: a CPU and GPU math expression compiler

The oronto face dataset

Learning Multiple Layers of Features from Tiny Images

The OpenCV Library. Dr. Dobb's Journal of Software Tools

Gradient-based learning applied to document recognition

Note sur la convergence de méthodes de directions conjuguées

Sur la division des corps mat´eriels en parties

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names