3 papers
cs.AI2026
NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung +2
Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their…
cs.LG2025
Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung +2
Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-statio…
cs.LG2024
Parseval Regularization for Continual Reinforcement Learning
Wesley Chung, Lynn Cherif, David Meger +1
Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the incr…