Overcoming catastrophic forgetting in neural networks

James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, +11

Proceedings of the National Academy of Sciences

Artificial IntelligenceLearning ProblemCognitive ScienceEngineeringMachine Learning +13

Progressive Neural Networks

Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, +5

arXiv (Cornell University)

Artificial IntelligenceIncremental LearningEngineeringMachine LearningSequential Learning +17

Theano: A CPU and GPU Math Compiler in Python

James Bergstra, Olivier Breuleux, Frédéric Bastien, +6

Proceedings of the Python in Science Conferences

EngineeringMachine LearningPython ModulesCompiler TechnologyMachine Learning Tool +16

Combining modality specific deep neural networks for emotion recognition in video

Samira Ebrahimi Kahou, Christopher Pal, Xavier Bouthillier, +24

EngineeringMachine LearningWild ChallengeMultimodal Sentiment AnalysisSocial Sciences +14

Understanding disentangling in $\beta$-VAE

Christopher Burgess, Irina Higgins, Arka Pal, +4

arXiv (Cornell University)

Understanding disentangling in $β$-VAE

Christopher Burgess, Irina Higgins, Arka Pal, +3

arXiv (Cornell University)

Quantum ScienceEngineeringMachine LearningPhysicsInformation Theory +8

Theano: Deep Learning on GPUs with Python

James Bergstra, Frédéric Bastien, Olivier Breuleux, +8

Unsupervised and Transfer Learning Challenge: a Deep Learning Approach

Grégoire Mesnil, Yann Dauphin, Xavier Glorot, +10

International Conference on Machine Learning

Few-shot LearningEngineeringMachine LearningData ScienceFeature Learning +13

Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines

Guillaume Desjardins, Aaron Courville, Yoshua Bengio, +2

International Conference on Artificial Intelligence and Statistics

EngineeringMachine LearningEntropyHidden Markov ModelRestricted Boltzmann Machines +6

Policy Distillation

Andrei A. Rusu, Sergio Gómez Colmenarejo, Çaǧlar Gülçehre, +6

arXiv (Cornell University)

Artificial IntelligenceComplex Visual TasksEngineeringMachine LearningDeep Reinforcement Learning +9