咨询与建议

限定检索结果

文献类型

  • 2 篇 期刊文献

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 教育学
    • 1 篇 教育学
    • 1 篇 心理学(可授教育学...
  • 2 篇 工学
    • 1 篇 控制科学与工程
    • 1 篇 计算机科学与技术...
  • 1 篇 理学
    • 1 篇 生物学
  • 1 篇 管理学
    • 1 篇 图书情报与档案管...

主题

  • 2 篇 class-incrementa...
  • 1 篇 deep learning
  • 1 篇 named entity rec...
  • 1 篇 few-shot learnin...
  • 1 篇 catastrophic for...
  • 1 篇 continual learni...
  • 1 篇 experience repla...

机构

  • 1 篇 information rese...
  • 1 篇 ieee
  • 1 篇 school of artifi...
  • 1 篇 college of compu...
  • 1 篇 center for resea...
  • 1 篇 the state key la...
  • 1 篇 center for resea...
  • 1 篇 the cas center f...

作者

  • 1 篇 zhen huang
  • 1 篇 yifan chen
  • 1 篇 da yu
  • 1 篇 kaiqi huang
  • 1 篇 mingyi zhang
  • 1 篇 feng liu
  • 1 篇 dongsheng li
  • 1 篇 minghao hu
  • 1 篇 lining sun
  • 1 篇 changjian wang
  • 1 篇 fusheng zha
  • 1 篇 xicheng lu
  • 1 篇 junge zhang
  • 1 篇 mantian li

语言

  • 2 篇 英文
检索条件"主题词=class-incremental learning"
2 条 记 录,以下是1-10 订阅
排序:
Squeezing More Past Knowledge for Online class-incremental Continual learning
收藏 引用
IEEE/CAA Journal of Automatica Sinica 2023年 第3期10卷 722-736页
作者: Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE
Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,kno... 详细信息
来源: 维普期刊数据库 维普期刊数据库 同方期刊数据库 同方期刊数据库 评论
Decoupled Two-Phase Framework for class-incremental Few-Shot Named Entity Recognition
收藏 引用
Tsinghua Science and Technology 2023年 第5期28卷 976-987页
作者: Yifan Chen Zhen Huang Minghao Hu Dongsheng Li Changjian Wang Feng Liu Xicheng Lu College of Computer National University of Defense TechnologyChangsha 410073China Information Research Center of Military Science PLA Academy of Military ScienceBeijing 100091China
class-incremental Few-Shot Named Entity Recognition(CIFNER)aims to identify entity categories that have appeared with only a few newly added(novel)class examples.However,existing class-incremental methods typically in... 详细信息
来源: 维普期刊数据库 维普期刊数据库 评论