Bahram Zonooz

A new method for improving neural networks' resistance to attacks while maintaining performance.

Introducing FOMO, a method to improve DNNs against adversarial attacks through forgetting.

Self-supervised learning improves model performance with less labeled data.

IMEX-Reg enhances machine learning by reducing forgetting and improving task performance.

Integrating multiple data types improves learning and retention in deep neural networks.

AGILE uses attention mechanisms to improve continual learning and reduce forgetting.

Introducing DARE, a method to improve machine learning without forgetting old knowledge.