Lectures

meeting backup: https://meet.google.com/dnr-uxfi-yay

1. Learning from Tabular data: slides

2. Learning from Relational data: slides

3. Graph Representation Learning: slides

4. Relational Deep Learning: slides

5. Neural-Symbolic Learning: slides

6. Learning with LLMs: slides

7. Interpretability in ML: slides

8. Markov decision processes: slides

9. Tabular RL: Q-Learning and SARSA

10. Deep RL: Deep Q-learning. Policy gradient.

11. A/B tests and multi-armed bandit problems, UCB algorithm.

12. Bayesian bandits (Thompson sampling). Contextual bandits.

13. Potential outcomes - Rubin-Neyman causal model, uplift modeling

14. Intro to “Pearl’s” causality