3 papers
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…
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…
Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning
Negin Hashemi Dijujin, Seyed Roozbeh Razavi Rohani, Mohammad Mahdi Samiei +1
Sample efficiency and systematic generalization are two long-standing challenges in reinforcement learning. Previous studies have shown that involving natural language along with o…