BriefGPT.xyz
Apr, 2021
再次训练的局限性和优点揭示：持续学习中重访样本的限度和优点
Rehearsal revealed: The limits and merits of revisiting samples in continual learning
HTML
PDF
Eli Verwimp, Matthias De Lange, Tinne Tuytelaars
TL;DR
本文探讨了不断学习中，使用rehearsal方法的优点和局限，通过三个基准测试提供了实证证据，指出使用该方法的模型在任务完成后仍然处于较低的损失区域，但有过拟合采样数据的风险从而降低模型的泛化能力，这是一项重要的持续学习研究。
Abstract
Learning from
non-stationary data streams
and overcoming
catastrophic forgetting
still poses a serious challenge for machine learning research. Rather than aiming to improve state-of-the-art, in this work we prov
→