Search Results for author:
Found 2 papers, 2 papers with code
Mitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning
Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge.
IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning
To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
