Neural Networks for Data Science
Master's Degree in Data Science (2026-2027)
Important Info
| News: register on Google Classroom for course news and updates. | |
| Timetable: Thursdays 09:00–12:00 and Fridays 09:00–11:00, room A5 (Via Ariosto), from 24 September to 18 December 2026 |
News
- Registration on Google Classroom is open.
General overview
The course provides a general overview on neural networks as compositions of differentiable blocks, that are optimized numerically. We describe common building blocks including convolutions, self-attention, batch normalization, etc., with a focus on images, texts, and graphs. The course combines rigorous mathematical descriptions with coding sessions in PyTorch / JAX, as well as an overview of the current AI landscape.
Material
The teaching materials repository contains the slide sources and shared PyTorch notebooks, including PT01 and PT02, which open directly in Colab.
Lab sessions are in blue. Homeworks and projects (mandatory) are in red. Seminars (optional) are in green.
| # | Date | Content | Materials | Reading |
|---|---|---|---|---|
| L0 | 24/09/26 | About the course | – | |
| L1 | 24/09/26 | (Historical) introduction | ||
| L2 | 25/09/26 | Preliminaries | ||
| PT01 | Introduction to PyTorch | – |
Book: Alice’s Adventures in a Differentiable Wonderland
The course is complemented by a book which expands on most topics covered during the lectures:
- Buy the book on Amazon (independently published to keep the price low).
- Downloaded the updated full draft (29/08/2025).
For the full book webpage (with arXiv version, errata list, and additional chapters): https://sscardapane.it/alice-book/