Pylearn2: a machine learning research library

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.

9 pages

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Theano: new features and speed improvements

Cited by in corpus (54)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Conditional Generative Adversarial Nets
• Explaining and Harnessing Adversarial Examples
• Brain Tumor Segmentation with Deep Neural Networks
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• FitNets: Hints for Thin Deep Nets
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Attention-Based Models for Speech Recognition
• Understanding Neural Networks Through Deep Visualization
• NICE: Non-linear Independent Components Estimation
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• Gated Feedback Recurrent Neural Networks
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Qualitatively characterizing neural network optimization problems
• Deep Learning in the Automotive Industry: Applications and Tools
• Discovering Hidden Factors of Variation in Deep Networks
• Blocks and Fuel: Frameworks for deep learning
• End-to-End Text Recognition with Hybrid HMM Maxout Models
• Improved Microaneurysm Detection using Deep Neural Networks
• Loss-aware Weight Quantization of Deep Networks
• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• Feature Representation in Convolutional Neural Networks
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Deep learning as a tool for neural data analysis: speech classification and cross-frequency coupling in human sensorimotor cortex
• An empirical analysis of dropout in piecewise linear networks
• Interlinked Convolutional Neural Networks for Face Parsing
• A Survey on Deep Learning Methods for Robot Vision
• Visual Causal Feature Learning
• Theano-based Large-Scale Visual Recognition with Multiple GPUs
• Recognizing Semantic Features in Faces using Deep Learning
• Representing high throughput expression profiles via perturbation barcodes reveals compound targets
• An Adaptive Learning Method of Restricted Boltzmann Machine by Neuron Generation and Annihilation Algorithm
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• A Unified Gradient Regularization Family for Adversarial Examples
• Deep Learning in Bioinformatics
• ShaResNet: reducing residual network parameter number by sharing weights
• Understanding Locally Competitive Networks
• ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient
• INsight: A Neuromorphic Computing System for Evaluation of Large Neural Networks
• Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images
• Multimodal Transitions for Generative Stochastic Networks
• All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification
• Unsupervised neural and Bayesian models for zero-resource speech processing
• From Maxout to Channel-Out: Encoding Information on Sparse Pathways
• Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards
• Deep Learning in Robotics: A Review of Recent Research
• Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
• Adaptive Normalized Risk-Averting Training For Deep Neural Networks
• Comprehensive and Efficient Data Labeling via Adaptive Model Scheduling
• Combination of Diverse Ranking Models for Personalized Expedia Hotel Searches
• On Binary Classification with Single-Layer Convolutional Neural Networks
• Cell identification in whole-brain multiview images of neural activation
• Empirical study of PROXTONE and PROXTONE${}^{+}$ for Fast Learning of Large Scale Sparse Models