Qihong Lu


Home

Research Projects

Academic CV

Tutorials

Resources


myGithub myEmail

myLinkedin myFacebook

myTwitter

Here're some resources for deep learning and reinforcement learning, primarily.

Online courses

Reinforcement Learning, David Silver, University College London
- Learning Reinforcement Learning, Denny Britz, Google Brain
Deep reinforcement learning, Sergey Levine, John Schulman, Chelsea Finn, UC Berkeley
Deep learning, Nando de Freitas, Oxford University
ConvNet for visual recognition, Fei-Fei Li, et al., Stanford University
- ConvNetJs: some online demo, by Andrej Karpathy
Intro to neural network, Hugo Larochelle, Université de Sherbrooke
Intro to machine learning, Tom Mitchell, Carnegie Mellon University
Understanding higher cognition, Andrew Coward, Australian National University


Books

Deep learning, Ian Goodfellow, Yoshua Bengio and Aaron Courville
Intro to reinforcement learning, Richard Sutton and Andrew Barto
The PDP handbook, Jay McClelland
Neural Networks and Deep Learning, Michael Nielsen

Other resources

Learning Deep Learning with Keras
Deep learning reading list 1 , reading list 2
Deep learning repo - books, courses, papers, data, etc.
Deep reinforcement learning papers
A reading list on Bayesian methods, Tom Griffiths
Tutorials on Bayesian Nonparametrics, Peter Orbanz
Blogs: Niko Kriegeskorte, Distill, Christopher Olah, Andrej Karpathy, Shakir Mohamed


Frameworks

Tensorflow: a reverse mode auto-differentiation library in Python
- Keras: a high level API built on top of Tensorflow.
- Neural Network Playground: Play with a feed-forward network!
- Model Zoo: Neural networks implemented in TensorFlow
OpenAI Gym: simulated environment for training RL agents
LENS: the light, efficient network simulator.
emergent: a comprehensive neural network simulator.