|
|
| Academic Year |
2024/2025 |
| Name |
Dott. - MI (1380) Ingegneria dell'Informazione / Information Technology |
| Programme Year |
1 |
| ID Code |
062767 |
| Course Title |
ADVANCED DEEP LEARNING |
| Course Type |
MONO-DISCIPLINARY COURSE |
| Credits (CFU / ECTS) |
5.0 |
| Course Description |
"Lectures are accompanied by practical lab sessions where students can practice on Colab the materials seen during lectures and also implement models for specific applications. The detailed program is the following:
- Course Introduction (2h): a historical perspective on Deep Learning with key steps in the evolution of learning techniques, deep learning models, and deep models investigation techniques.
- Deep learning in non-supervised settings (4h+3h): Unsupervised DL models (AutoEncoders), self-supervised learning practices for pre-training, metric-based and zero-shot learning, knowledge distillation. Deep Learning Models for Anomaly Detection and Image Restoration.
- The Transformers (4h+3h): The Attention Mechanism and the Transformers (in natural language processing). The Attention mechanism in images and Vision Transformers, Self-supervised Learning for Images, Contrastive Learning / Multimodal Learning (e.g., DINO, CLIP, etc).
- Generative AI (4h+3h): Advanced models for Image generation, Normalizing Flows, Diffusion Models, DALL-E and text-conditional image generation.
- Deep Models investigation techniques (4h+3h): Explainability tools for Deep Neural Networks (e.g., saliency maps) and adversarial attacks with countermeasures." |
| Scientific-Disciplinary Sector (SSD)
|
|
SSD Code
|
SSD Description
|
CFU
|
|
ING-INF/05
|
INFORMATION PROCESSING SYSTEMS
|
5.0
|
|
|
Alphabetical group
|
Name
|
Teaching Assignment Details
|
|
From (included)
|
To (excluded)
|
|
A
|
ZZZZ
|
Matteucci Matteo, Boracchi Giacomo, Mentasti Simone
|
|
|
