BriefGPT.xyz
Aug, 2023
提升连续学习中的回放样本选择和存储,减少遗忘
Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning
HTML
PDF
Daniel Brignac, Niels Lobo, Abhijit Mahalanobis
TL;DR
通过对常用的蓄水池采样方法与其他替代人群策略进行比较,本研究旨在解决连续学习中选择最具信息价值样本和确定最优存储样本数量的问题,并提供了相关的详细分析。
Abstract
continual learning
seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the
catastrophic forgetting
of previous tasks. One effective solution is
→