跳到主要导航 跳到搜索 跳到主要内容

Characterization of degree of approximation for neural networks with one hidden layer

  • China Jiliang University
  • Xi'an Jiaotong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

There have been various studies on approximation ability of feedforward neural networks (FNNs). Most of the existing studies are, however, only concerned with density or upper bound estimation on how a function can be approximated by an FNN, and consequently, the essential approximation ability of an FNN can not been revealed. In this paper, by establishing both upper and lower bound estimations on degree of approximation, the essential approximation ability of a class of FNNs is clarified in terms of the modulus of smoothness of functions to be approximated. The involved FNNs can not only approximate any continuous functions arbitrarily well, but also provide an explicit lower bound on number of hidden units required. By making use of approximation tools, it is shown that when the functions to be approximated are Lipschitzian, the approximation speed of the FNNs is determined by modulus of smoothness of the functions.

源语言英语
主期刊名Proceedings of the 2006 International Conference on Machine Learning and Cybernetics
页2944-2947
页数4
DOI
出版状态已出版 - 2006
活动2006 International Conference on Machine Learning and Cybernetics - Dalian, 中国
期限: 13 8月 2006 → 16 8月 2006

丛书

姓名Proceedings of the 2006 International Conference on Machine Learning and Cybernetics
卷2006

会议

会议2006 International Conference on Machine Learning and Cybernetics
国家/地区中国
市Dalian
时期13/08/06 → 16/08/06

学术指纹

探究 'Characterization of degree of approximation for neural networks with one hidden layer' 的科研主题。它们共同构成独一无二的学术指纹。

引用此