计算机工程2025，Vol.51Issue(6)：57-64,8.DOI:10.19678/j.issn.1000-3428.0069310
一种基于块平均正交权重修正的连续学习算法
A Continuous Learning Algorithm Based on Block Average and Orthogonal Weight Modification
摘要
Abstract
Continuous learning ability is an important aspect of human intelligent behavior,which enables humans to acquire new knowledge continuously.However,several studies have shown that conventional deep neural networks do not possess such continuous learning capabilities.After learning new tasks in sequence,they often experience catastrophic forgetting of previously learned tasks,which hinders the continuous accumulation of new knowledge and limits further improvement in intelligence.Therefore,enabling deep neural networks to have continuous learning capabilities is important to achieve strong artificial intelligence technologies.This study proposes a continuous learning algorithm based on block average and orthogonal weight modification,named B-OWM,which uses a set of input sample block average vectors with an extremely optimal number of blocks to represent the input space,combined with the idea of Orthogonal Weight Modification(OWM)to update network parameters.Thus,deep neural network models can overcome catastrophic forgetting of learned knowledge when learning new tasks.Many incremental continuous learning experiments on multiple datasets with nonoverlapping tasks show that B-OWM algorithm significantly outperforms the OWM algorithm in terms of continuous learning performance,with an accuracy improvement rate of up to 80％in continuous learning scenarios with large batch number.关键词
连续学习/正交权重修正/深度学习/正则化/灾难性遗忘Key words
continuous learning/Orthogonal Weight Modification(OWM)/deep learning/regularization/catastrophic forgetting分类
计算机与自动化引用本文复制引用
廖丁丁,刘俊峰,曾君,邱晓欢..一种基于块平均正交权重修正的连续学习算法[J].计算机工程,2025,51(6):57-64,8.基金项目
国家自然科学基金(62173148,52377186) （62173148,52377186）
广东省普通高校重点领域专项(新一代信息技术)(2021ZDZX1136). （新一代信息技术）
