Sumários

Reinforcement learning

15 Maio 2023, 16:30 • Luís Miguel Parreira e Correia

Reinforcement learning
Bellman's dynamic programming
Q-learning
Exploitation v. exploration

Exercises on adversarial attacks

9 Maio 2023, 14:00 • Helena Aidos

Exercises on adversarial attacks on learning models.

Exercises on adversarial attacks

8 Maio 2023, 18:30 • Helena Aidos

Exercises on adversarial attacks on learning models.

Adversarial ML

8 Maio 2023, 16:30 • Luís Miguel Parreira e Correia

Attacks on learning models: membership inference analysis, mitigation strategies

   

Exercises on interpretability models

2 Maio 2023, 14:00 • Helena Aidos

Exercises on interpretability models using Mean Decrease in Impurity, Permutation Feature Importance, SHAP and LIME.