提出新型自组织映射，缓解持续学习中的遗忘问题。
SatSOM: Saturation Self-Organizing Maps for Continual Learning
- 引入饱和机制，随信息积累自动降低学习率与邻域范围
- 冻结已充分训练神经元，将学习聚焦未充分利用区域
- 适合需要长期记忆的AI系统，如智能机器人
持续学习对神经网络构成根本挑战，通常在处理顺序任务时出现灾难性遗忘。自组织映射（SOM）虽具可解释性与高效性，却同样面临此问题。本文提出饱和自组织映射（SatSOM），一种增强版SOM，旨在提升持续学习中的知识保留能力。SatSOM引入新颖的饱和机制，使神经元在积累信息后逐步降低学习率与邻域半径，有效冻结已充分训练的神经元，并将学习过程引导至地图中尚未充分利用的区域。
原文摘要 · Abstract (English)
Continual learning poses a fundamental challenge for neural systems, which often suffer from catastrophic forgetting when exposed to sequential tasks. Self-Organizing Maps (SOMs), despite their interpretability and efficiency, are not immune to this issue. In this paper, we introduce Saturation Self-Organizing Maps (SatSOM)-an extension of SOMs designed to improve knowledge retention in continual learning scenarios. SatSOM incorporates a novel saturation mechanism that gradually reduces the learning rate and neighborhood radius of neurons as they accumulate information. This effectively freezes well-trained neurons and redirects learning to underutilized areas of the map.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。