Statistics
- Maximum Likelihood, Fisher Information, Cramer Rao Inequality []
- Importance Sampling []
- Variational Lower Bounds (ELBO) []
Machine Learning
Deep Learning
- Understanding how increasing the number of layers increases the training error after a point and how Resnets solve it []
- Do neural nets generalize better with larger data sets? []
- Overcoming local minima problem in neural networks []
- Why do activation functions need to be non-linear? []
Reinforcement Learning
- Lecture 10 - Applying RL to Games [Notes] []
- Lecture 9 - Advanced Exploration [Notes] []
- Lecture 8 - Integrating Learning and Planning [Notes] []
- Lecture 7 - Policy Gradients [Notes] []
- Lecture 6 - Value Function Approximation [Notes] []
- Lecture 5 - Optimizing Model Free Techniques (Model Free Control) [Notes] []
- Lecture 4 - Model Free Techniques - MC and TD[Notes] []
- Lecture 3 - Dynamic Programming in RL [Notes] []
- Lecture 2 - Markov Processes [Notes] []
- Lecture 1 - Introduction to Reinforcement Learning [Notes] []
- Relation between Dynamic Programming and Reinforcement Learning []