A Python implementation of well-known dictionary learning methods.
PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, GR, GR+distill, RtF, ER, A-GEM, iCaRL).
Evaluate various supervised learning methods to predict cohesive energies of solids (kernel ridge regression is the best)
STScI INS training
A curated list of awesome Machine Learning frameworks, libraries and software.
Asynchronous Methods for Deep Reinforcement Learning
Several SSL methods (Pi model, Mean Teacher) are implemented in pytorch
Using a paper from Google DeepMind I've developed a new version of the DQN using threads exploration instead of memory replay as explain in here: http://arxiv.org/pdf/1602.01783v1.pdf I used the one-step-Q-learning pseudocode, and now we can train the Pong game in less than 20 hours and without any GPU or network distribution.
stock predictor with random forest tree