Explainable Artificial Intelligence

Period of duration of course
‌‌
Course info
Number of course hours
30
Number of hours of lecturers of reference
20
Number of hours of supplementary teaching
10
CFU 3
‌‌

Modalità esame

Relazione di seminario

Lecturer

View lecturer details

Docenti di didattica integrativa

Lecturer

View lecturer details

Programma

1) Module1 (10 hours):  Crush course on XAI. 

a.      Motivation for XAI: 

i.     Why explanation and What is an explanation 

ii.     The taxonomy of XAI methods for Machine Learning

b.     Overview post-hoc explanation methods 

c.      Overview of transparent by-design methods


2)     Module2 (10 hours): Advanced Concepts 

a.      Counterfactual explanations

b.     Explaining by design – argumentation and knowledge graph

c.      Explaining by design & Global Explainer: on the integration of symbolic and sub-symbolic 

d.     Interactive XAI – the new research challenges in XAI

e.      Student seminars


3)     Module3 (10 hours):  Hands-on: on XAI methods.  (By Roberto Pellungrini)

a.      The students will be introduced to python library of XAI-Lib methods for tabular data (4h)    

b.     The students will be introduced to python library of XAI methods for images data (4h)

c.      The students will be introduced to some global explanation method (2h)

Obiettivi formativi

This (30 hours) course provides a reasoned introduction to the work of Explainable AI (XAI) to date, and surveys the literature with a focus on post-hoc and by-design approaches.  We motivate the needs of XAI in real-world and large-scale application, while presenting state-of-the-art techniques and best practices, as well as discussing the many open challenges. An XAI platform with collection of many of the recently proposed algorithms will be presented on specific use cases and it will be possible familiarize with some of the methods.

The course is organized as follows in three modules: i) an introductory one providing motivations, main concepts and main methods; ii) an advanced one where the students will actively participate to monographs topics with readings interleaved with interventions of international scholars working on the sector; iii) an hands-on module where the students will be introduced to the usage on XAI methods.


Moduli

Modulo Ore CFU Docenti
Explainable Artificial Intelligence 20 3 Fosca Giannotti
Supplementary Teaching 10 0 Roberto Pellungrini