期刊文献+

多值多门限神经元函数的相关性和频谱分析 被引量:1

Correlation and Spectrum Analysis of Functions Implemented by Multi-value Multi-threshold Neurons
下载PDF
导出
摘要 为衡量单个多值多门限神经元的计算能力,引入了与多值多门限神经元函数有关的2个代数几何概念:相关性和扩展频谱.利用相关性,给出对于一组固定的输入函数,不同输出函数个数的上限.利用扩展频谱,给出为了使得神经元能够计算任意输出函数,所需输入函数个数的下限.这2个界限,给出了单个多值多门限神经元的计算能力.同时,输入函数个数的下限,给出了当用多值多门限神经元组成的三层前馈神经网络实现任意多值函数时,网络复杂度的下限. In order to scale the computational ability of a single multi-value multi-threshold neuron,this paper introduces two geometrical concepts:correlation and generalized spectrum.By using the correlation,we give the upper bound of the number of different output functions for a group of fixed input functions.By using the generalized spectrum,we give the lower bound of the number of input functions in order to realize arbitrary output functions.This lower bound is also the lower bound of the complexity of a three...
作者 姜楠 章照止
出处 《北京工业大学学报》 EI CAS CSCD 北大核心 2009年第4期549-554,共6页 Journal of Beijing University of Technology
基金 北京市优秀人才培养资助项目(20061D0501500191) 北京工业大学博士科研启动基金资助项目(52007016200701) 北京工业大学校青基金资助项目(X1007016200801).
关键词 多值多门限 神经元 相关性 频谱 multi-value multi-threshold neuron correlation spectrum
  • 相关文献

参考文献1

二级参考文献2

  • 1杨行峻,人工神经网络,1992年
  • 2吴佑寿

共引文献14

同被引文献17

  • 1姚茂群,朱晓雷,沈继忠.多阈值神经元电路设计及在多值逻辑中的应用[J].计算机学报,2005,28(2):281-288. 被引量:3
  • 2王守觉.多值和多阈值神经元及其网络组合与应用[J].电子学报,1996,24(5):1-6. 被引量:15
  • 3NGOM A, STOJMENOVIC l, MILUTINOVIC V. STRIP: a strip-based neural-network growth algorithm for learning multiple-valued functions[ J]. IEEE Transactions on Neural Networks, 2001, 12(2) : 212-227.
  • 4OJHA P. Enumeration of linear threshold functions from the lattice of hyperplane intersections [ J ]. IEEE Transactions on Neural Networks, 2000, 11 (4) : 839- 850.
  • 5SIU K, ROYCHOWDHURY V, KAILATH T. Discrete neural computation: a theoretical foundation [ M ]. Englewood Cliffs, NJ: Prentice-Hall, 1995 : 1- 114, 265- 308.
  • 6ZHANG Zhao-zhi, MA Xiao-min, YANG Yi-xian. Bounds on the number of hidden neurons in three-layer binary neural networks [J]. Neural Networks, 2003, 16: 995- 1002.
  • 7YUH J, NEWEOMB R W. Circuits for multi-level neuron nonlinearities [ C ]// Proceedings of International Joint Conference on Neural Networks. Baltimore: IEEE Computer Society Conference Publishing Services, 1992: 27-32.
  • 8JIANG Nan, YANG Yi-xian, MA Xiao-min, et al. Using three layer neural network to compute multi-valued functions [ C ] // Proceedings of Fourth International Symposium on Neural Networks, Part III, LNCS 4493. Nanjing: Springer, 2007: 1-8.
  • 9WANG Jian, YANG Yi-xian, JIANG Nan, et al. Using three layer neural networks to compute discrete real functions [ C ] // Proceedings of 3rd International Conference on Natural Computation Computer Society Conference Publishing 446-450. Haikou : IEEE Services, 2007 :.
  • 10JIANG Nan, ZHANG Zhao-zhi, MA Xiao-min, et al. Analysis of nonseparable property of multi-valued multi- threshold neuron [ C ]//Proceedings of 2008 IEEE World Congress on Computational Intelligence. Hong Kong: IEEE Computer Society Conference Publishing Services, 2008 : 414-420.

引证文献1

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