eXplainable Machine Learning / Wyjaśnialne Uczenie Maszynowe - 2024/25

eXplainable Machine Learning course for Machine Learning (MSc) studies at the University of Warsaw.

Winter semester 2024/25 @pbiecek @hbaniecki @sobieskibj

Previous year: eXplainableMachineLearning-2024, eXplainableMachineLearning-2023, eXplainableMachineLearning-2022

Meetings

Plan for the winter semester 2024/2025. MIM_UW classes are on Fridays.

• 2024-10-04 -- Introduction, Slides, Audio, Extra reading: Lipton 2017
• 2024-10-11 -- Fairness, Slides, Extra reading: Fairness and Machine Learning
• 2024-10-18 -- LIME and friends, Slides, Audio, Extra reading: Why Should I Trust You?, LORE
• 2024-10-25 -- Ethics and AI 1/3
• 2024-11-08 -- SHAP and friends
• 2024-11-15 -- PDP and friends
• 2024-11-22 -- Ethics and AI 2/3
• 2024-11-29 -- PROJECT: showcase (in-person presentations)
• 2024-12-06 -- VIP and friends
• 2024-12-13 -- LRP and friends
• 2024-12-20 -- Counterfactual explanations and friends
• 2025-01-10 -- Student presentations of research papers
• 2025-01-17 -- Ethics and AI 3/3
• 2025-01-24 -- PROJECT: final presentation (in-person presentations)

How to get a good grade

The final grade is based on activity in four areas:

• mandatory: Project (0-36)
• mandatory: Exam (0-30)
• optional: Homeworks (0-24)
• optional: Presentation (0-10)

In total you can get from 0 to 100 points. 51 points are needed to pass this course.

Grades:

• 51-60: (3) dst
• 61-70: (3.5) dst+
• 71-80: (4) db
• 81-90: (4.5) db+
• 91-100: (5) bdb

Homeworks (0-24 points)

• Homework 1 - Fairness for 0-4 points. Deadline: 2024-10-18 (graded by PBI)
• Homework 2 - LIME for 0-4 points. Deadline: 2024-11-08 (graded by BSO)
• Homework 3 - SHAP for 0-4 points. Deadline: 2024-11-15 (graded by HBA)
• Homework 4 - PDP for 0-4 points. Deadline: 2024-12-06 (graded by PBI)
• Homework 5 - VIP for 0-4 points. Deadline: 2024-12-13 (graded by BSO)
• Homework 6 - LRP for 0-4 points. Deadline: 2024-12-20 (graded by HBA)

Project (0-35 points)

TODO

Literature

We recommend to dive deep into the following books and explore their references on a particular topic of interest:

• Explanatory Model Analysis. Explore, Explain and Examine Predictive Models by Przemysław Biecek, Tomasz Burzykowski
• Fairness and Machine Learning: Limitations and Opportunities by Solon Barocas, Moritz Hardt, Arvind Narayanan
• Interpretable Machine Learning. A Guide for Making Black Box Models Explainable by Christoph Molnar