Will Grathwohl

JEM. Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"

VERA. Python

GWG_release. Official release of code for "Oops I Took A Gradient: Scalable Sampling for Discrete Distributions"

LSD. Official Release of "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling"

BackpropThroughTheVoidRL. RL Experiments from our paper "Backpropagation Through the Void": https://arxiv.org/abs/1711.00123. Lovingly forked from OpenAI's RL Baseline repo.

captcha_crusher. Neural networks for solving image captchas

flows. Python

snf. will plays around with stochastic normalizing flows

reparamer. houses utilities for reparameterization gradients for nonstandard distributions

tf_magic_init. Implementation of (https://arxiv.org/pdf/1511.06856v2.pdf) in tensorflow.

JAXFlows. Will wants to learn JAX. He will implement flows.

improved_contrastive_divergence. Python

Spaghetti-DQL. This is an implementation of Deep Q Learning and a simple game engine to test it.

inference_sandbox. A simple sandbox environment build on top of tensorflow for testing variational inference algorithms

DeepLearningRefuse. A dump of some of my deep learning projects from the past year. Includes adversarial models and variational autoencoders

noreward-rl. [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

text_gen. Conditional Text Generation

gans-n-gmms. Official implementation of "On GANs and GMMs"

compressed_rnn. Compressing RNN's and stuff