Search Results for author:
Found 3 papers, 0 papers with code
Investigating the Impact of Weight Sharing Decisions on Knowledge Transfer in Continual Learning
Through this lens we demonstrate how task complexity and similarity influence the optimal weight sharing decisions, giving insights into the relationships between tasks and helping inform decision making in similar CL methods.
A Theoretical Perspective on Subnetwork Contributions to Adversarial Robustness
To better understand these attacks and facilitate more efficient adversarial training, in this paper we develop a novel theoretical framework that investigates how the adversarial robustness of a subnetwork contributes to the robustness of the entire network.
Theoretical Understanding of the Information Flow on Continual Learning Performance
Despite the numerous previous solutions to bypass the catastrophic forgetting (CF) of previously seen tasks during the learning process, most of them still suffer significant forgetting, expensive memory cost, or lack of theoretical understanding of neural networks' conduct while learning new tasks.
