Teacher
Roberto Confalonieri
Department of Information Engineering
roberto.confalonieri[at]dei.unipd.it
INFO-01/A

Aim
The aim of this course is to underscore the importance of Explainable AI, introduce various explanation methods and techniques, and demonstrate the role of ontologies in enhancing the perceived understandability of explanations for user

Syllabus
- A historical perspective of Explainable AI
- Taxonomy of explanation and evaluation approaches
- Model-specific explanation approaches
- Model-agnostic explanation approaches
- The role of ontologies in Explainable AI

Introductory reading
C. Molnar Interpretable Machine Learning: A Guide for Making Black Box Models Explainable https://christophm.github.io/interpretable-ml-book/

Course requirements
- Basic notions of supervised machine learning (from the BMCS course on Tools and applications of machine learning)

Examination modality
None

Course material, enrollment and last minute notifications
Made available by the teacher at this Moodle address

Schedule
05 March 2025, 14:30-17:30
12 March 2025, 14:30-17:30

Location
Tbd

<< Courses in 2024-2025