Survey on Replay-Based Continual Learning and Empirical Validation on Feasibility in Diverse Edge Devices Using a Representative Method

The goal of on-device continual learning is to enable models to adapt to streaming data without forgetting previously acquired knowledge, even with limited computational resources and memory constraints. Recent research has demonstrated that weighted regularization-based methods are constrained by i...

詳細記述

書誌詳細

主要な著者:	Heon-Sung Park, Hyeon-Chang Chu, Min-Kyung Sung, Chaewoon Kim, Jeongwon Lee, Dae-Won Kim, Jaesung Lee
フォーマット:	Artigo
言語:	Inglês
出版事項:	MDPI AG 2025-07-01
シリーズ:	Mathematics
主題:	continual learning replay sparse update on-device edge device
オンライン･アクセス:	https://www.mdpi.com/2227-7390/13/14/2257
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!