Teaching
Explainable and Interpretable AI (PhD Course, 3 CFU, 2024)
The course will introduce basic concepts related to explaining and debugging neural network models, including feature attribution methods, data attribution methods, and counter-factual explanations. The course will have both theory and practical sessions, and additional seminars from guest speakers.
Fondamenti di Machine Learning (6 CFU)
Bachelor level course for students of the Bachelor’s Degree in Communication Engineering, introducing basic concepts of machine learning both from a theoretical and from a practical perspective.
Neural Networks for Data Science Applications (6 CFU)
Master level course for students of the Master’s Degree in Data Science, describing the basic ideas of deep learning applied to different types of data.
Previous years: [2020-2021] | [2021-2022] | [2022-2023] | [2023-2024]
Neural Networks (6 CFU)
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 (Master’s Degree in AI and Robotics, co-taught with Prof. Danilo Comminiello).
Previous years: [2022-2023]
Deep Learning Seminars (PhD Course, 3 CFU, 2022)
The seminars will cover several advanced topics in deep learning: meta learning (i.e., “learning to learn”), continual learning (i.e., learning from a continuous stream of tasks), and data engineering for deep learning (i.e., preparing data for being used in deep learning pipelines).
Reproducible Deep Learning (PhD Course, 3 CFU, 2021)
PhD Course for the Data Science program, describing tools and idea to produce reproducible models and experiments (Git, DVC, Docker, …).