SatSOM：用于持续学习的饱和自组织映射
SatSOM: Saturation Self-Organizing Maps for Continual Learning
AI总结：
SatSOM通过引入饱和机制，逐步降低神经元的学习率和邻域半径，以提升持续学习中的知识保留能力。
摘要：
持续学习对神经系统提出了根本性挑战，因为神经网络在面对连续任务时常常遭遇灾难性遗忘。自组织映射（SOMs）尽管具有可解释性和效率，但也不免受到这一问题的影响。本文介绍了一种自组织映射的扩展形式——饱和自组织映射（SatSOM），旨在改进持续学习场景中的知识保留能力。SatSOM引入了一种新颖的饱和机制，随着神经元积累信息，逐步降低其学习率和邻域半径。这有效冻结了已良好训练的神经元，并将学习引导至映射中未充分利用的区域。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
