BriefGPT.xyz
Jun, 2022
人体状态监测的持续学习
Continual Learning for Human State Monitoring
HTML
PDF
Federico Matteoni, Andrea Cossu, Claudio Gallicchio, Vincenzo Lomonaco, Davide Bacciu
TL;DR
本文提出了两个与实际环境相似的CL基准，分别用于人类状态监测中，研究结果表明，由于基准具有增量属性，遗忘容易被解决，现有策略在固定测试对象上累积知识方面存在困难。
Abstract
continual learning
(CL) on
time series data
represents a promising but under-studied avenue for real-world applications. We propose two new CL benchmarks for
→