期刊文献+

基于超立方体覆盖的构造性网络学习算法 被引量:2

Constructive training algorithm based on hypercube covering
原文传递
导出
摘要 该文提出了一种基于超立方体覆盖的构造性神经网络学习算法,以解决二值型输入变量的K分类问题。该算法分两步来动态地构造一个三层前馈网络。首先,对于每一类的所有训练样本,用尽可能少的超立方体来覆盖它们,并为每一个超立方体构造一个隐层单元;其次,用"或"操作把这些隐单元连接到相应的输出单元上。文章给出了相应的理论分析和一个具体的实现。实验结果表明,该算法优于常用的一些归纳学习算法。 A constructive training algorithm based on hypercube covering was developed for classification problems involving binaryvalued input attributes and multiple output classes. The algorithm dynamically constructs a threelayer feedforward neural network in two stages. First, for all the training examples in each class, the algorithm finds a set of hypercubes to cover the examples with each hypercube corresponding to a hidden neuron. Then, these neurons are connected to the corresponding output unit using the OR operation. The algorithm is analyzed theoretically and illustrated by an example. The results show that the method is superior to other commonly used inductive algorithms.
出处 《清华大学学报(自然科学版)》 EI CAS CSCD 北大核心 2003年第1期97-100,共4页 Journal of Tsinghua University(Science and Technology)
基金 国家自然科学基金重点资助项目(60135010) 国家"九七三"重点基础研究资助项目(G1998030509)
关键词 构造性网络学习算法 人工神经网络 构造法 超立方体覆盖 BP算法 K分类 二值型输入变量 artificial neural networks constructive algorithm hypercube covering
  • 相关文献

参考文献7

  • 1张钹,张铃.人工神经网络的设计方法[J].清华大学学报(自然科学版),1998,38(S1):4-7. 被引量:9
  • 2Young S A. Constructive Neural Network Training Algorithm for Pattern Classification Using Computational Geometry Techniques [D]. Queensland: University of Queensland,1996.
  • 3Marchand M,Golea M,Rujan P. A convergence theorem for sequential learning in two-layer perceptrons [J]. Europhysics Letters,1990,11(6): 487-492.
  • 4Denker J,Schwartz D,Wittner S,et al. Large automatic learning rule extraction and generalization [J]. Complex Systems,1987,1: 877-922.
  • 5Gray D L,Michel A N. A training algorithm for binary feedforward neural network [J]. IEEE Trans Neural Networks,1992,3(2): 176-194.
  • 6Mascioli F M F,Martinelli G. A constructive algorithm for binary neural networks: the oil-spot algorithm [J]. IEEE Trans Neural Networks,1995,6(3): 794-797.
  • 7张铃,张钹,殷海风.多层前向网络的交叉覆盖设计算法[J].软件学报,1999,10(7):737-742. 被引量:158

二级参考文献3

共引文献163

同被引文献10

引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部