Teacher

Lorenza Brusini

Referent

Lorenza Brusini

Credits

5

Language

English

Class attendance

Free Choice

Location

VERONA

Moodle Seminars 0

Learning objectives

Artificial Intelligence has become a fundamental instrument in fields like biomedicine and neurosciences, from the discovery of new numerical biomarkers to support to the diagnosis. However, especially in the previously mentioned fields, the machine and deep learning methods employed for the analysis are often seen as black box due to the million of mathematical operations they perform. Explainable models have been developed with the precise scope of shedding light on the mechanisms leading to the results. Based on this premise, this course aims at providing the students knowledge about the main machine learning methods and explainable models at the state of the art that are mostly exploited in the field, providing both theoretical bases and implementation tools.

Prerequisites and basic notions

The laboratory sessions will be in Python.

Program

- Fundamentals of AI: machine learning step-by-step
- Opening the black box: the eXplainable Artificial Intelligence
- The main models in the light of explainability
- A hint into agnostic post-hoc explainability models

Didactic methods

The participation to the course will be fully in person. Each lecture will start by setting the theoretical bases of the following hands-on session. In particular, the hands-on sessions will include both the illustration and discussion of pieces of code and the exercises for students aiming at solving the considered problem.

Learning assessment procedures

Development of a brief project consisting of the application of what learned during the lessons.

Assessment

Correct application of what learned during the course

Criteria for the composition of the final grade

Pass/Fail

Scheduled Lessons