Vai ai contenuti. | Spostati sulla navigazione | Spostati sulla ricerca | Vai al menu | Contatti | Accessibilità

logo del sistema bibliotecario dell'ateneo di padova

Piccolini, Michele (2016) Network Architecture of Unsupervised Boltzmann Machines. [Laurea triennale]

Full text disponibile come:

[img]
Preview
PDF
2954Kb

Abstract

Our thesis wants to illustrate recent developments in ANN, and study the topological properties of a specific type of ANN using tools from graph theory. The work is divided in two main parts. First, it presents useful concepts and models. We then focus on understanding the mode of operation of a Deep Belief Network (DBN), a multi-layer neural network that works under the unsupervised learning framework. The second part of this work analyzes a trained DBN (qualified on reading digits images from the popular MNIST database ADD REF) from a network perspective. We inspect the topological properties of the DBN, making use of graph theory. The goal of this unprecedented analysis is to seek a deeper knowledge of the topological modifications that the DBN experiences during the training.

Item Type:Laurea triennale
Corsi di Laurea Triennale:Scuola di Scienze > Fisica
Uncontrolled Keywords:Neural network, Boltzmann machine, Network Architecture
Subjects:Area 02 - Scienze fisiche > FIS/02 Fisica teorica, modelli e metodi matematici
Codice ID:53476
Relatore:Suweis, Samir
Data della tesi:September 2016
Biblioteca:Polo di Scienze > Dip. Fisica e Astronomia "Galileo Galilei" - Biblioteca
Tipo di fruizione per il documento:on-line per i full-text

Solo per lo Staff dell Archivio: Modifica questo record