APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS

Zhang Junying; Xu Jin; Bao Zheng

Volume 23 Issue 9

Sep. 2001

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2001 > 23(9): 879-889

Zhang Junying, Xu Jin, Bao Zheng . APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS[J]. Journal of Electronics & Information Technology, 2001, 23(9): 879-889.

Citation:

Zhang Junying, Xu Jin, Bao Zheng . APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS[J]. Journal of Electronics & Information Technology, 2001, 23(9): 879-889.

Zhang Junying, Xu Jin, Bao Zheng . APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS[J]. Journal of Electronics & Information Technology, 2001, 23(9): 879-889.

Citation:

Zhang Junying, Xu Jin, Bao Zheng . APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS[J]. Journal of Electronics & Information Technology, 2001, 23(9): 879-889.

PDF( 1939 KB)

APPROACHES ON ATTRACTION CHARACTORISTICS OF A KIND OF DISCRETE HOPFIELD NETWORKS

Received Date: 1999-10-15
Rev Recd Date: 2000-04-29
Publish Date: 2001-09-19

Abstract

Abstract

This paper studies the attraction characteristics of a kind of symmetric discrete Hopfield neural networks, the network with ri-cube as its structure and connection situation, called n-cube network. The structure of the attraction states/cycles and their attraction diameters are explored. The result is that the attraction region is of same size and so is the attraction diameters for the attraction states/cycles with same attraction structure. Furthermore, the above result is extended to a more general asymmetric discrete Hopfield network and the conditions for the network to be (or partially to be) with the same attraction states/cycles as those of n-cube network are studied, and its attraction diameters are presented.

FullText(HTML)

References(1)

References

许进,保铮,超立方体的谱,工程数学学报,1999,16(4),1-5.[2]汪云九,神经信息的编码,97中国神经计算大会论文集(CCNS97),武汉,1997,Vol.1,32-37[3]张军英,许进,保铮,一类离散Hopfield网络的吸引状态的特征分析,电子与信息学报,2001,23(7),677 686[4]阎平凡,黄端旭,人工神经网络-模型,分析与应用,合肥安徽教育出版社,1991年,第三章[5]董继扬,徐慎初,王新明,均匀分类DHNN的几何描述,97中国神经计算大会论文集(CCNS97),武汉,1997.Vol.2.288-292.[6]张军英,许进,保铮,Hopfield网络的关联分析,自动化学报,1997,23(4),446-454.[7]廖晓昕,昌莉,离散Hopfield神经网络的稳定性研究,自动化学报,1999,25(6),721-727 ［8］F. Luccio, L. Pagli, On a new Boolean function with applications, IEEE Trans. on Computers,1999, 48(3), 296-310.[8]董继扬,徐慎初,可用几何方法描述分类性能的神经网络的构造,神经网络理论与应用研究96,成都,西南交通大学出版社,1996,129-133.[9]J.J. Hopfield, Neural networks and physical system with emergent collective computer abilities,Proc. Natl. Acad. USA, 1982, 79(4), 2554-2558.

Relative Articles

Supplements(0)

Cited By

Proportional views