Simone Marullo When: Jun 29th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Learning to Prompt for Continual Learning The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known […]

Giuseppe Alessio D’Inverno (University of Siena) When: Jun 8th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description 1-Lipschitz Neural Networks: a splines-based approach Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better […]