持续学习中Fisher信息的计算研究
On the Computation of the Fisher Information in Continual Learning
AI总结：
针对深度神经网络持续学习中弹性权重整合（EWC）方法的Fisher信息计算方式描述缺失、实现多样的问题，本文实证比较多种常用实现，发现改变计算方式可提升EWC结果。
摘要：
深度神经网络持续学习最流行的方法之一是弹性权重整合（EWC），该方法涉及Fisher信息的计算。然而，Fisher信息的具体计算方式鲜有描述，且在线可找到多种不同实现。本文讨论并实证比较了几种常用实现，结果表明，通过改变Fisher信息的计算方式，当前许多EWC相关报告结果可能得到改善。
英文摘要：
One of the most popular methods for continual learning with deep neural networks is Elastic Weight Consolidation (EWC), which involves computing the Fisher Information. The exact way in which the Fisher Information is computed is however rarely described, and multiple different implementations for it can be found online. This blog post discusses and empirically compares several often-used implementations, which highlights that many currently reported results for EWC could likely be improved by changing the way the Fisher Information is computed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
