Variance-Covariance Regularization Improves Continual Learning

In this work, we explore the benefits of Variance-Covariance Regularization in Continual Learning (CL). Neural networks suffer from abrupt performance loss when updated with additional data. Numerous CL approaches try to mitigate this problem by preserving the already accumulated knowledge within th...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Piotr Hondra, Daniel Marczak, Kamil Deja
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Continual learning regularization representation learning
Online Access:	https://ieeexplore.ieee.org/document/11142694/