EXplainable Artificial Intelligence (XAI) recently emerged as one of the hottest topics aimed at overcoming this limitation by proposing strategies for understanding the why and the how of the outcomes of Machine (ML) and Deep Learning (DL), allowing to disentangle the contributions of the different features of the input shaping the CNN final output.

Explainable deep learning for decrypting disease signatures in multiple sclerosis

Federica Cruciani
;
Lorenza Brusini;Mauro Zucchelli;Gustavo Retuci Pinheiro;Francesco Setti;Rachid Deriche;Leticia Rittner;Massimiliano Calabrese;Ilaria Boscolo Galazzo;Gloria Menegaz
2023-01-01

Abstract

EXplainable Artificial Intelligence (XAI) recently emerged as one of the hottest topics aimed at overcoming this limitation by proposing strategies for understanding the why and the how of the outcomes of Machine (ML) and Deep Learning (DL), allowing to disentangle the contributions of the different features of the input shaping the CNN final output.
2023
9780323960984
Explainable Deep Learning, Multiple Sclerosis, Layerwise Relevance Propagation
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1091128
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact