Explainability in deep learning models applied to spatio-temporal problems

Day - Time: 13 September 2024, h.11:00

Place: Area della Ricerca CNR di Pisa - Room: C-29

Speakers

• Javier Garcia Siguenza (University of Alicante)

Referent

Mirco Nanni

Abstract

Artificial Intelligence (AI) is transforming society, affecting everything from industry to decision making, and concerns about its transparency have increased. Explainable Artificial Intelligence (XAI) is crucial to address this problem, allowing to obtain a better understanding of its behavior, thus being able to help in both ethical and technical aspects. However, the application of explainability techniques together with spatio-temporal problems represents a challenge due to the reduced number of options, which when implemented penalize performance in exchange for the explainability obtained.