Deep neural networks and thermodynamics

Squadrani, Lorenzo (2020) Deep neural networks and thermodynamics. [Laurea], Università di Bologna, Corso di Studio in Fisica [L-DM270], Documento full-text non disponibile
Il full-text non è disponibile per scelta dell'autore. (Contatta l'autore)

Abstract

Deep learning is the most effective and used approach to artificial intelligence, and yet it is far from being properly understood. The understanding of it is the way to go to further improve its effectiveness and in the best case to gain some understanding of the "natural" intelligence. We attempt a step in this direction with the aim of physics. We describe a convolutional neural network for image classification (trained on CIFAR-10) within the descriptive framework of Thermodynamics. In particular we define and study the temperature of each component of the network. Our results provides a new point of view on deep learning models, which may be a starting point towards a better understanding of artificial intelligence.

Abstract
Tipologia del documento
Tesi di laurea (Laurea)
Autore della tesi
Squadrani, Lorenzo
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
Deep Learning,Machine Learning,Artificial Intelligence,Thermodynamics and Data science,Thermodynamics and Deep Learning,Physics and Deep Learning,Physics and Artificial intelligence,Convolutional,Neural,Network,image classification,applied physics
Data di discussione della Tesi
18 Settembre 2020
URI

Altri metadati

Gestione del documento: Visualizza il documento

^