Philip Bachman's repositories
amdim-public
Public repo for Augmented Multiscale Deep InfoMax representation learning
Pseudo-Ensembles
Materials for implementing and reproducing results in the NIPS paper.
MatNets-NIPS
Repo for code for the NIPS paper entitled "An Architecture for Deep, Hierarchical Generative Models"
NN-Dropout
This code is for training feedforward neural networks with dropout.
Sequential-Generation
Generative models and other stuff too, maybe, perhaps even probably
MultiClassBoosting
Code for a variety of approaches to learning classifiers via boosting
Matrix-Learning
Code for algorithms and tests pertaining to sparse network basis learning
paper-notes
Random notes on papers, likely a short-term repo.
Pragmatic-Bandits
code for performing pragmatic banditry