一类离散Hopfield网络吸引状态的特征分析
EIGENVECTOR ANALYSIS OF SZABLE STATES FOR A KIND OF DISCRETE HOPFIELD NETWORKS
-
摘要: 该文首先讨论了超立方体图所对应的连接矩阵的特征向量,进而深入系统地分析了以n维超立方体为大规模局域连接模型的离散Hopfield网络的吸引特性之一,稳定吸引状态的位置、数量及其分布。研究结果表明,网络连接权矩阵的特征向量及其拼接向量均为网络的吸引子或吸引环,且其在网络状态空间中具有均匀对称的分布格局。Abstract: The eigenvector of n-cube graph is found and then a kind of Hopfield networks with n-cube as its structure and connection situation, called n-cube network, are analysed theoretically for the attractions states/cycles and their distribution in the state space of the network. The analysis shows that the eigenvectors of the connection matrix of the network and their linkages are, in general, either the attraction states or attraction cycles of the net, and the distribution of these states/cycles is symmetric and uniform in state space of the network.
-
许进,保铮,超立方体的谱,工程数学学报,1999,(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 132-37.[3]F. Luccio, L. Pagli, On a new Boolean function with applications, IEEE Trans. on Computers.1999, 48(3), 296-310.[4]R.J. Lechner, Harmonic Analysis of Switching Functions, Recent Development in SwitchingTheory, Washinton: Academic Press, 1971, 122-229.[5]北京大学数学系,高等代数,北京,高等教育出版社,1988年第二版,第五章[6]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.[7]J..J. Hopfield, Neural networks and physical system with emergent collective computer abilities.Proc. Natl. Acad. USA, 1982, 79(3), 2554-2558.[8]Li Yujian, Wang Xiangdong, Chen Chuan, The maximum number of orthogonal memory patterns,Proc. of 1998 International Conference on Neural Networks and Brain(ICNN B98), Beijing,1998, 79-81.[9]张军英,许进,保铮,一类离散Hopfield网络的吸引特性研究,电子与信息学报,2001,23(9),872-882. -
计量
- 文章访问数: 2038
- HTML全文浏览量: 112
- PDF下载量: 651
- 被引次数: 0
下载:
