Lifelong Learning Needs Sleep: Few-Shot Incremental Learning Enhanced by Sleep

Yuma Kishimoto, Koichiro Yamauchi

2025

Abstract

Catastrophic forgetting due to incremental learning in neural networks is a serious problem. We demonstrate that introducing a sleep period can address this issue from two perspectives. First, it provides a learning period for re-learning old memories. Second, it allows for time to process new learning. We applied a VAE, enhanced by an adapter, for incremental learning of new samples and generating valid samples from a few learning examples. These generated samples are used for the neural network’s re-learning, which also contributes to improving its generalization ability. The experimental results suggest that this approach effectively realizes few-shot incremental learning.

Paper Citation

in Harvard Style

Kishimoto Y. and Yamauchi K. (2025). Lifelong Learning Needs Sleep: Few-Shot Incremental Learning Enhanced by Sleep. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 243-250. DOI: 10.5220/0013170200003905

in Bibtex Style

@conference{icpram25,
author={Yuma Kishimoto and Koichiro Yamauchi},
title={Lifelong Learning Needs Sleep: Few-Shot Incremental Learning Enhanced by Sleep},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={243-250},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013170200003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Lifelong Learning Needs Sleep: Few-Shot Incremental Learning Enhanced by Sleep
SN - 978-989-758-730-6
AU - Kishimoto Y.
AU - Yamauchi K.
PY - 2025
SP - 243
EP - 250
DO - 10.5220/0013170200003905
PB - SciTePress