Neural Networks

The course is intended as a broad overview to neural networks, as used today in a number of applicative fields. It provides a strong theoretical and practical understanding of how neural networks and modern deep networks are designed and implemented, highlighting the most common components, ideas, and current limitations. We will review the general paradigm of building differentiable models that can be optimized end-to-end with gradient descent from data, and then overview essential components to design architectures able to work on images (convolutive layers), sequences (recurrent layers), and sets (transformer layers). The last part of the course will then focus on a selection of emerging research topics, including generative models, among others.

Calendar: 23 September - 17 December, 2025.

Class Schedule: Tuesday 13:00 - 16:00 Classroom A3, DIAG, Via Ariosto, 25
Wednesday 14:00 - 16:00 Classroom A3, DIAG, Via Ariosto, 25

Material: Slides, notebooks, assignments, and news will be available on the course's Google Classroom. Students are invited to register.

Teachers

Exams

Exams must be booked electronically via the INFOSTUD portal. Scheduled exam sessions for the year 2024/2025:

• Session I: XX January 2026 - Classroom, Address, Time

• Session II: XX February 2026 - Classroom, Address, Time

• Extraordinary Session I: XX March 2026 - Classroom, Address, Time

• Session III: XX June 2026 - Classroom, Address, Time

• Session IV: XX July 2026 - Classroom, Address, Time

• Session V: XX September 2026 - Classroom, Address, Time

• Extraordinary Session II: XX October 2026 - Classroom, Address, Time