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.
View on arXiv@article{urbanik2025_2506.10680,
title={ Saturation Self-Organizing Map },
author={ Igor Urbanik and Paweł Gajewski },
journal={arXiv preprint arXiv:2506.10680},
year={ 2025 }
}