• Lecture 1 - ML, MAP, K Nearest Neighbors.

• Lecture 2 - Gaussian Mixture Models.

• Lecture 3 - Linear and logistic regression.

• Lecture 4 - Neural networks: Back Propagation.

• Lecture 5 - Overfitting, Regulazation and Dropout.

• Lecture 6 - Decision Trees & MDL.

• Lecture 7 - Tree Distribution.

• Lecture 8 - Sequential ML. Recurrent Neural Networks (RNN), Long Short Time Memory (LSTM).

• Lecture 9 - MINE. Mutual Information Neural Estimation (MINE) and hypothesis testing.

• Lecture 10 - f Divergence. f-Divergence and Data Processing Inequality.

• Lecture 11 - Variational Inference.

• Lecture 12 - Variational Autoencoders: Version 1, Version 2.

Appendix:

• Appendix 1- Information measures [pdf].

Additional materials

• Information Theory course - recommended.

• Reinforcement Learning Course - recommended after undertanding the fundementals of this course.

• Python tutorial.