====== Lectures ======

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

1.	 	Learning from Tabular data: {{ :courses:becm36mlm:lectures:mlm_week_1.pdf | slides}}

2.	 	Learning from Relational data: {{ :courses:becm36mlm:lectures:mlm_week_2.pdf | slides}}

3.	 	Graph Representation Learning: {{ :courses:becm36mlm:lectures:mlm_week_3.pdf | slides}}

4.	 	Relational Deep Learning: {{ :courses:becm36mlm:lectures:mlm_week_4.pdf | slides}}

5.	 	Neural-Symbolic Learning: {{ :courses:becm36mlm:lectures:mlm_week_5.pdf | slides}}

6.	 	Learning with LLMs: {{ :courses:becm36mlm:lectures:mlm_week_6.pdf | slides}}

7.	 	Interpretability in ML: {{ :courses:becm36mlm:lectures:mlm_week_7.pdf | slides}}

8.	 	Markov decision processes: {{ :courses:becm36mlm:lectures:lecture_8_presentation_2026.pdf | slides}}

9.	 	Tabular RL I. {{ :courses:becm36mlm:lectures:mlm_lecture_9.pdf | slides}}

10.	 	Tabular RL II. (We will continue with the slides from week 9).

11.	 	Deep RL: Deep Q-learning. Policy gradient. 
Intro to Bandits: A/B tests and multi-armed bandit problems, UCB algorithm. {{ :courses:becm36mlm:lectures:mlm_lecture_11.pdf | Deep RL slides}} {{ :courses:becm36mlm:lectures:bandits-intro-ucb.pdf | Bandits slides}}

12.	 	Bayesian bandits (Thompson sampling). Contextual bandits. Policy gradient (finishing RL from Week 12). {{ :courses:becm36mlm:lectures:thompson_sampling.pdf | Thompson Sampling slides}} {{ :courses:becm36mlm:lectures:mlm_lecture_11.pdf | Deep RL slides}}

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

14.	 	Intro to “Pearl’s” causality