Gian Hess

Guglielmo Bonifazi, Iason Chalas, Gian Hess et al.

This paper explores the connection between two recently identified phenomena in deep learning: plasticity loss and neural collapse. We analyze their correlation in different scenarios, revealing a significant association during the initial training phase on the first task. Additionally, we introduce a regularization approach to mitigate neural collapse, demonstrating its effectiveness in alleviating plasticity loss in this specific setting.