[tensorflow] Hello World

Environment: MacOS X

Installing with Anaconda: https://www.tensorflow.org/install/install_mac#installing_with_anaconda

• Install Anaconda
• Create a conda environment named tensorflow
• conda create -n tensorflow 
• To activate this environment, use: source activate tensorflow
• To deactivate this environment, use: source deactivate tensorflow
• Install TensorFlow inside your conda environment
• Install jupyter inside your conda environment
• pip install jupyter
• jupyter notebook

Run softmax regression on MNIST: https://www.tensorflow.org/get_started/mnist/beginners

• https://github.com/Meng-Gen/docs/blob/master/tf/mnist_softmax.ipynb

Run Deep MNIST: https://www.tensorflow.org/get_started/mnist/pros

• https://github.com/Meng-Gen/docs/blob/master/tf/mnist_pros.ipynb

Reference:

• How do Convolutional Neural Networks work?
• http://brohrer.github.io/how_convolutional_neural_networks_work.html
• Useful packages: 
• ml_metrics: pip install ml_metrics

[FWD] UCL Course on RL

http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html

(Video Lecture 1: https://www.youtube.com/watch?v=2pWv7GOvuf0)

Textbooks:

• An Introduction to Reinforcement Learning, Sutton and Barto, 1998 
• MIT Press, 1998 
• ∼ 40 pounds 
• Available free online! 
• http://people.inf.elte.hu/lorincz/Files/RL_2006/SuttonBook.pdf
• Algorithms for Reinforcement Learning, Szepesvari Morgan and Claypool, 2010 
• ∼ 20 pounds 
• Available free online! 
• https://sites.ualberta.ca/~szepesva/papers/RLAlgsInMDPs.pdf