A Brain-Inspired Distributed Long-Term Memory Guided Online Continual Learning Method

Yuyang Han, Xiuxing Li, Qixin Wang, Tianyuan Jia, Xia Wu*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Online Continual Learning (CL) is a challenging scenario that focuses on enabling models to incrementally learn new knowledge from sequential, non-i.i.d. data with only a single pass through the data. Replay-based methods have shown great potential in this scenario, but they still suffer from catastrophic forgetting. In contrast, the human brain exhibits great advantages in online CL scenario, with memories swiftly encoded as short-term memories in the hippocampus and subsequently consolidated into distributed long-term memories within the neocortex. Inspired by this neural mechanism, we introduce the Distributed Long-Term Memory Guided CL(DLTMG-CL) method, which guides the network to retain old knowledge while learning new information by consolidating and preserving distributed long-term memories. This approach facilitates efficient learning in online CL scenario. Our algorithm has achieved state-of-the-art (SOTA) performance among various CL methods.

Original languageEnglish
Title of host publicationHuman Brain and Artificial Intelligence - 4th International Workshop, HBAI 2024, Proceedings
EditorsQuanying Liu, Youzhi Qu, Haiyan Wu, Yu Qi, An Zeng, Dan Pan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages331-343
Number of pages13
ISBN (Print)9789819640003
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024 - Jeju, Korea, Republic of
Duration: 3 Aug 20243 Aug 2024

Publication series

NameCommunications in Computer and Information Science
Volume2438 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024
Country/TerritoryKorea, Republic of
CityJeju
Period3/08/243/08/24

Keywords

  • Brain-inspired Method
  • Catastrophic Forgetting
  • Continual Learning
  • Online Continual Learning

Fingerprint

Dive into the research topics of 'A Brain-Inspired Distributed Long-Term Memory Guided Online Continual Learning Method'. Together they form a unique fingerprint.

Cite this