BriefGPT.xyz
Jun, 2020
最优连续学习具有完美记忆且是NP难问题
Optimal Continual Learning has Perfect Memory and is NP-hard
HTML
PDF
Jeremias Knoblauch, Hisham Husain, Tom Diethe
TL;DR
本文提出了一个理论方法来解释在连续学习任务中避免遗忘的可行性和困难性，主要发现是实现这样的算法通常需要解决NP问题和具有完美的内存存储能力。此发现在经验回放、情景记忆和核心集等方面的CL算法表现出的优异表现相对于基于正则化方法是有理论基础的。
Abstract
continual learning
(CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and avoid so-called
catastrophic forgetting
→