BriefGPT.xyz
Sep, 2019
一项继续学习调查:在分类任务中应对遗忘
Continual learning: A comparative study on how to defy forgetting in classification tasks
HTML
PDF
Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia...
TL;DR
本文研究了基于任务增量分类的持续学习方法,提出了一种新的框架来确定持续学习者的稳定性与可塑性的权衡, 并通过三个基准测试以及综合实验比较了11种持续学习方法和4种基线的方法的强弱和影响。
Abstract
artificial neural networks
thrive in solving the
classification
problem for a particular rigid task, where the network resembles a static entity of knowledge, acquired through generalized learning behaviour from
→