List of machine learning resources I found most valuable
- Graphical Models, Exponential Families, and Variational Inference, Jordan, Wainwright
- Classic HMM Intro Paper Rabiner
- Introduction to Markov Random Fields
- Introduction to Kalman- and Bayesian-Filters (Book as a jupyter notebook)
- Bayesian Modeling in Python
- Monte Carlo method intro Video, Iain Murray NIPS2015
- MCMC Sampling intro/tutorial
- Online Book on Probabilistic Generative Models, Goodman, Tenenbaum
- Intro/Intuition on Variational Inference (e.g. KLqp vs. KLpq dist.div.) D.MacKay Lecture
- Advanced Inference in Graphical Models - Youtube Lectures J.Bilmes
- Edward python lib / Paper
- pyMC3 for Bayesian Modeling
- Harnessing Deep Neural Networks with Logic Rules
- Zero-Shot Learning for Semantic Utterance Classification - 2015 Dauphin et al.
- Neural Machine Translation - seq2seq, ICLR 2015 Bahdanau, Cho, Bengio
- Grammar as a foreign language, 2014 Vinyals, Kaiser, Koo, Petrov, Sutskever, Hinton
- Pointer Networks, 2015 Vinyals, Fortunato, Jaitly
- Neural GPUS Learn Algortihms - 2016 Kaiser, Sutskever (Multilayer CGRU - generalizing to 2000bit length ops w/o error)
- Video Frame Generation via Cross Convolution
- OpenAI: Generative Adversarial Imitation Learning
- Unsup. feature disentangling - InfoGAN
- Wasserstein GAN
- The numerics of GANs / Consensus Optimization
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- DeepMind paper on deep RL (Deep Q-Learning, experience replay)
- Deep Reinforcement Learning with Double Q-learning
- Predicting distributions with Linearizing Belief Networks
- Weakly supervised memory networks, 2015 Sukhbaatar, Szlam, Weston, Fergus
- Arxiv Sanity Preserver
- Stanford Unsupervised Feature Learning and Deep Learning
- ML @ Stanford cheatsheet
- NIPS2014 Workshop list/videos
- Online Book D.McKay: Information Theory,Inference,and Learning Algorithms
- What is the intuition behind a beta distribution
- sugartensor lib on top of tensorflow (e.g. Quasi-RNN reference impl)
- Python