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: 25 September - 18 December, 2026.

Class Schedule: Tuesday 13:00 - 16:00 Classroom A3, DIAG, Via Ariosto, 25
Friday 12:00 - 14:00 Classroom A5, 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 2026/2027:

• Session I: - January 2027 - TBD

• Session II: - February 2027 - TBD

• Extraordinary Session I: - March/April 2027 - TBD

• Session III: - June 2027 - TBD

• Session IV: - July 2027 - TBD

• Session V: - September 2027 - TBD

• Extraordinary Session II: XX October 2027 - TBD