BriefGPT.xyz
Apr, 2020
应对少样本问题中的灾难性遗忘
Bayesian Online Meta-Learning with Laplace Approximation
HTML
PDF
Pau Ching Yap, Hippolyt Ritter, David Barber
TL;DR
引入一种贝叶斯在线元学习框架来解决少样本分类问题中的灾难性遗忘问题,并通过实验验证与各种基线方法相比可以有效地实现该目标。
Abstract
neural networks
are known to suffer from
catastrophic forgetting
when trained on sequential datasets. While there have been numerous attempts to solve this problem for large-scale supervised classification, littl
→