咨询与建议

限定检索结果

文献类型

  • 3 篇 期刊文献

馆藏范围

  • 3 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 3 篇 工学
    • 3 篇 计算机科学与技术...
    • 1 篇 电气工程
    • 1 篇 控制科学与工程

主题

  • 3 篇 exponentiated gr...
  • 1 篇 riemannian metri...
  • 1 篇 gradient descent...
  • 1 篇 kernelization
  • 1 篇 relative loss bo...
  • 1 篇 natural gradient
  • 1 篇 matching loss fu...
  • 1 篇 link-functions
  • 1 篇 gradient descent
  • 1 篇 sigmoid transfer...
  • 1 篇 multiplicative u...
  • 1 篇 rotational invar...
  • 1 篇 generalized line...

机构

  • 2 篇 univ calif santa...
  • 1 篇 australian natl ...
  • 1 篇 univ helsinki de...
  • 1 篇 poznan univ tech...
  • 1 篇 xidian univ sch ...
  • 1 篇 australian natl ...

作者

  • 1 篇 warmuth mk
  • 1 篇 zhou shuisheng
  • 1 篇 williamson rc
  • 1 篇 mahony re
  • 1 篇 kotlowski wojcie...
  • 1 篇 helmbold dp
  • 1 篇 kivinen j
  • 1 篇 warmuth manfred ...

语言

  • 2 篇 英文
  • 1 篇 其他
检索条件"主题词=Exponentiated Gradient algorithm"
3 条 记 录,以下是1-10 订阅
排序:
Prior knowledge and preferential structures in gradient descent learning algorithms
收藏 引用
JOURNAL OF MACHINE LEARNING RESEARCH 2001年 第4期1卷 311-355页
作者: Mahony, RE Williamson, RC Australian Natl Univ Dept Engn Canberra ACT 0200 Australia Australian Natl Univ Dept Telecommun Engn Res Sch Informat Sci & Engn Canberra ACT 0200 Australia
A family of gradient descent algorithms for learning linear functions in an online setting is considered. The family includes the classical LMS algorithm as well as new variants such as the exponentiated gradient (EG)... 详细信息
来源: 评论
Kernelization of matrix updates, when and how?
收藏 引用
THEORETICAL COMPUTER SCIENCE 2014年 第C期558卷 159-178页
作者: Warmuth, Manfred K. Kotlowski, Wojciech Zhou, Shuisheng Univ Calif Santa Cruz Dept Comp Sci Santa Cruz CA 95064 USA Poznan Univ Tech Inst Comp Sci Poznan Poland Xidian Univ Sch Math & Stat Xian 710071 Peoples R China
We define what it means for a learning algorithm to be kernelizable in the case when the instances are vectors, asymmetric matrices and symmetric matrices, respectively. We can characterize kernelizability in terms of... 详细信息
来源: 评论
Relative loss bounds for single neurons
收藏 引用
IEEE TRANSACTIONS ON NEURAL NETWORKS 1999年 第6期10卷 1291-1304页
作者: Helmbold, DP Kivinen, J Warmuth, MK Univ Calif Santa Cruz Dept Comp Sci Santa Cruz CA 95064 USA Univ Helsinki Dept Comp Sci FIN-00014 Helsinki Finland
We analyze and compare the well-known gradient descent algorithm and the more recent exponentiated gradient algorithm for training a single neuron with an arbitrary transfer function. Both algorithms are easily genera... 详细信息
来源: 评论