Tutorials

1. Learning from Tabular data - https://drive.google.com/file/d/1B9XhJTXlolqfgaUTuQ36ct9OrlBj9zjT/view?usp=sharing

2. Learning from Relational data - https://drive.google.com/file/d/1GkH7xaXgZVU-I4hV_5TdDE2os9OpNW-f/view?usp=sharing

3. Graph Neural Networks - https://drive.google.com/file/d/1PCKRrnyKJmdl-3_G3c0_9OVrfleUCD2A/view?usp=sharing

4. Relational Deep Learning - https://drive.google.com/file/d/14eKH7lS8fy9z3Iv5y74zmir65OBNzPVx/view?usp=sharing

5. Neural-Symbolic Learning - https://colab.research.google.com/drive/1j0I2RHhN_c5kjdH3vjh2-RJ1eG-grCGf?usp=sharing

6. Learning with LLMs - https://colab.research.google.com/drive/1m9UXEiSO6cjVhhKFWlk-Yc7GVjh3dhhs?usp=sharing

7. Interpretability in ML - https://colab.research.google.com/drive/1bSh4in8g792xBkYVpM8xQLOEO0XrlWjW?usp=sharing

8. Markov decision processes - MP and MRP exercises

9. Tabular RL I. - MDP exercises

10. Tabular RL II. https://github.com/supertweety/Minesweeper/blob/main/minesweeper_tabular_rl_exercise.ipynb

11. Deep RL: Deep Q-learning. Policy gradient. https://github.com/supertweety/Minesweeper/blob/main/minesweeper_deep_rl_exercise.ipynb

12. A/B tests and multi-armed bandit problems, UCB algorithm. Bayesian bandits (Thompson sampling). Contextual bandits.

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

14. Intro to “Pearl’s” causality