logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-09202022-100012


Tipo di tesi
Tesi di laurea magistrale
Autore
LEPRI, MARCO
URN
etd-09202022-100012
Titolo
Deep Learning for Compression of Physical Systems
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA
Relatori
relatore Bacciu, Davide
relatore Della Santina, Cosimo
Parole chiave
  • autoencoders
  • deep learning
  • graph neural networks
  • model order reduction
Data inizio appello
07/10/2022
Consultabilità
Non consultabile
Data di rilascio
07/10/2092
Riassunto
The thesis focuses on the proposal of method, based on deep learning, for performing compression of physical systems and the subsequent analysis of the characteristics and proerties of the reduced system. The method uses autoencoding neural networks to produce a compressed representation of the physical system which can be used to derive a new compressed system of equations describing the dynamic. The method is experimentally validated on mass-spring models by using the compressed system to perform their simulation. Moreover, the compressed representations are analyzed to have insights on the role of their variables and how the reconstructed system changes when varying their size. Finally, part of the work focus on trying to produce a model that is able to compress multiple and new systems.
File