SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning

06/08/2022
by   Fahad Sarfraz, et al.
14

Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective replay. It further employs synaptic consolidation by tracking the importance of parameters during the training trajectory and anchoring them to the consolidated parameters in the semantic memory. To the best of our knowledge, our study is the first to employ dual memory experience replay in conjunction with synaptic consolidation that is suitable for general CL whereby the network does not utilize task boundaries or task labels during training or inference. Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs.

READ FULL TEXT

page 7

page 8

page 13

page 14

page 15

research
01/29/2022

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Humans excel at continually learning from an ever-changing environment w...
research
06/27/2022

On-device Synaptic Memory Consolidation using Fowler-Nordheim Quantum-tunneling

Synaptic memory consolidation has been heralded as one of the key mechan...
research
12/28/2022

Sparse Coding in a Dual Memory System for Lifelong Learning

Efficient continual learning in humans is enabled by a rich set of neuro...
research
02/26/2020

Metaplasticity in Multistate Memristor Synaptic Networks

Recent studies have shown that metaplastic synapses can retain informati...
research
09/09/2022

Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling

Learning new tasks and skills in succession without losing prior learnin...
research
09/10/2021

Saliency Guided Experience Packing for Replay in Continual Learning

Artificial learning systems aspire to mimic human intelligence by contin...
research
06/11/2020

Understanding Regularisation Methods for Continual Learning

The problem of Catastrophic Forgetting has received a lot of attention i...

Please sign up or login with your details

Forgot password? Click here to reset