|
Anno Accademico |
2024/2025 |
Corso di Studi |
Dott. - MI (1380) Ingegneria dell'Informazione / Information Technology |
Anno di Corso |
1 |
Codice Identificativo |
062777 |
Denominazione Insegnamento |
INTERPRETABILITY AND EXPLAINABILITY IN MACHINE LEARNING |
Tipo Insegnamento |
MONODISCIPLINARE |
Crediti Formativi Universitari (CFU) |
5.0 |
Programma sintetico |
"Machine Learning Interpretability and Explainability are attracting a lot of interest along with the increase in the popularity and complexity of ML techniques. The goal of this course is to provide the students with an overview of this emerging field and a toolset of methods they can effectively apply in practice.
At the end of this course, students should be able to:
(i) understand the foundations and the basic principles of interpretability and explainability of machine learning models and their predictions;
(ii) design a machine learning solution that can fit a real-world decision process with strong interpretability and explainability requirements;
(iii) explain the model outputs and be able to provide an example-based explanation of a model;
(iv) deal with the challenges of designing an innovation process that involves machine learning techniques." |
Settori Scientifico Disciplinari (SSD) |
Codice SSD
|
Descrizione SSD
|
CFU
|
ING-INF/05
|
SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
|
5.0
|
|
Scaglione
|
Nome
|
Programma dettagliato
|
Da (compreso)
|
A (escluso)
|
A
|
ZZZZ
|
Loiacono Daniele
|
|
|