machine-learning-exercises

Draft: Machine Learning (Deep vs Reinforcement) experiments presented as Jupyter-notebooks (Scala)

Example1. Integration with Octave and R

Example2. Simple bandit (slot-machine) algorithm for reinforcement learning

Example3. Multi-layer network trained on MNIST digits (using deeplearning4j library)

Resources:

• "Reinforcement Learning: An Introduction" Richard S. Sutton and Andrew G. Barto
• "Deep Learning" Ian Goodfellow et al.

P.S. It's best to view examples in nbviewer, so you could get plot renderings for Scala-scripts.