|
Anno Accademico |
2024/2025 |
Corso di Studi |
Dott. - MI (1380) Ingegneria dell'Informazione / Information Technology |
Anno di Corso |
1 |
Codice Identificativo |
062767 |
Denominazione Insegnamento |
ADVANCED DEEP LEARNING |
Tipo Insegnamento |
MONODISCIPLINARE |
Crediti Formativi Universitari (CFU) |
5.0 |
Programma sintetico |
"The Deep Learning (DL) revolution has been pervasive in science and engineering, opening new perspectives in several domains, and achieving super-human performance in solving many complex tasks in language and visual understanding.
Advanced Deep Learning course aims at exploring two major directions in deep learning to provide an advanced ground to engineers aiming at up-to-date deep learning expertise that goes beyond a master-level course in deep learning:
- Advanced Deep Learning Architectures, such as Graph Neural Networks, Point Convolutional Networks, and Transformers, have recently introduced a breakthrough in DL research
- Learning non-conventional tasks (image generation with and without text conditioning) and from limited supervision (e.g., unsupervised / self-supervised / zero-shot learning). In particular, we will describe the mainstream models for generating images with d Diffusion models." |
Settori Scientifico Disciplinari (SSD) |
Codice SSD
|
Descrizione SSD
|
CFU
|
ING-INF/05
|
SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
|
5.0
|
|
Scaglione
|
Nome
|
Programma dettagliato
|
Da (compreso)
|
A (escluso)
|
A
|
ZZZZ
|
Matteucci Matteo, Boracchi Giacomo, Mentasti Simone
|
|
|