From a general perspective, the most impressive results [1, 6] in Machine Learn- ing have been recently obtained via black-box models, being Deep Neural Net- works (DNNs) the major player in the game. Nowadays, the same wonder that Eugene Wigner expressed for the unreasonable effectiveness of mathematics in describing physical world in the sixties of last century [7], should and is to a certain degree permeating computer scientists concerning the ability that com- puters show of solving complex tasks, often better than expert humans [3].

Deep Neural Networks and Explainable Machine Learning

Maratea, Antonio
;
Ferone, Alessio
2019-01-01

Abstract

From a general perspective, the most impressive results [1, 6] in Machine Learn- ing have been recently obtained via black-box models, being Deep Neural Net- works (DNNs) the major player in the game. Nowadays, the same wonder that Eugene Wigner expressed for the unreasonable effectiveness of mathematics in describing physical world in the sixties of last century [7], should and is to a certain degree permeating computer scientists concerning the ability that com- puters show of solving complex tasks, often better than expert humans [3].
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/11367/73851
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 0
social impact