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: 27 September - 21 December, 2023.
Class Schedule: Wednesday 14:00 - 16:00 Classroom 201, Viale Regina Elena, 295
Thursday 15:00 - 19:00 Classroom 15, SPV, Via Eudossiana, 18
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 2023/2024:
Session I: 17 January 2024 - 14:00 - Classroom 108 Marco Polo, Viale dello Scalo S. Lorenzo, 82 RM021
Session II: 2 February 2024 - 10:00 - Classroom 108 Marco Polo, Viale dello Scalo S. Lorenzo, 82 RM021Â
Extraordinary Session I: 8 April 2024 - 14:30 - Classroom A6, Via Ariosto
Session III: 17 June 2024 - 10:00 (To be confirmed)
Session IV: 10 July 2024 - 10:00 (To be confirmed)
Session V: 16 September 2024 - 10:00 (To be confirmed)
Extraordinary Session II: 22 October 2024 - 10:00 (To be confirmed)