典型文献
Quantum Continual Learning Overcoming Catastrophic Forgetting
文献摘要：
Catastrophic forgetting describes the fact that machine learning models will likely forget the knowledge of previ-ously learned tasks after the learning process of a new one.It is a vital problem in the continual learning scenario and recently has attracted tremendous concern across different communities.We explore the catastrophic forget-ting phenomena in the context of quantum machine learning.It is found that,similar to those classical learning models based on neural networks,quantum learning systems likewise suffer from such forgetting problem in classi-fication tasks emerging from various application scenes.We show that based on the local geometrical information in the loss function landscape of the trained model,a uniform strategy can be adapted to overcome the forget-ting problem in the incremental learning setting.Our results uncover the catastrophic forgetting phenomena in quantum machine learning and offer a practical method to overcome this problem,which opens a new avenue for exploring potential quantum advantages towards continual learning.
文献关键词：
中图分类号：
作者姓名：
Wenjie Jiang;Zhide Lu;Dong-Ling Deng
作者机构：
Center for Quantum Information,IIIS,Tsinghua University,Beijing 100084,China;Shanghai Qi Zhi Institute,Shanghai 200232,China
文献出处：
引用格式：
[1]Wenjie Jiang;Zhide Lu;Dong-Ling Deng-.Quantum Continual Learning Overcoming Catastrophic Forgetting)[J].中国物理快报（英文版）,2022(05):26-38
A类：
Continual,Catastrophic
B类：
Quantum,Learning,Overcoming,Forgetting,forgetting,describes,fact,that,machine,learning,models,will,likely,knowledge,previ,ously,learned,tasks,after,process,new,one,It,vital,problem,continual,scenario,recently,has,attracted,tremendous,concern,across,different,communities,We,explore,catastrophic,phenomena,context,quantum,found,similar,those,classical,neural,networks,systems,likewise,suffer,from,such,fication,emerging,various,application,scenes,show,local,geometrical,information,loss,function,landscape,trained,uniform,strategy,can,adapted,overcome,incremental,setting,Our,results,uncover,offer,practical,method,this,which,opens,avenue,exploring,potential,advantages,towards
AB值：
0.583667
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
