随机Hopfield神经网络的定量分析
THE QUANTITATIVE ANALYSIS OF STOCHASTIC HOPFIELD NEURAL NETWORK MODEL
-
摘要: 该文探讨了实际使用Hopfield神经网络(HNN)时噪声的影响。由于噪声的客观存在,我们首先证明了随机Hopfield神经网络(SHNN)轨道的期望关于时间是一致有界的。之后,为了实际设计神经网络的需要,我们对含有噪声的HNN和与其对应的一般HNN之间随机输入误差的估计进行了研究。利用所得的结论,我们可以对设计空间进行控制,使得所设计的网络满足我们希望获得的各种性能要求。Abstract: In this paper, the effect of input noise on the typical stochastic Hopfield neural network modei is discussed. It is shown that the expectation of the stochastic HNN of the trajectory is uniformly bounded over time. For practical design purposes, the stochastic input error estimates for the stochastic HNN with respect to the corresponding deterministic HNN is derived. In addition, the designer can use these results to constrain the design space so that the achieved design satisnes the performance specifications whenever possible.
-
徐秉铮,张百灵,韦岗,神经网络理论与应用,广州,华南理工大学出版社, 1994,第二章.[2]廖桂生,焦李成,保铮,神经网络随机扰动稳定性研究,电子科学学刊,1992,14(4),416-419.[3]武宝亭,李庆士,畅跃武,随机过程与随机微分方程,成都,电子科技大学出版社, 1994,第八章.[4]M A.Colen,S.Grossberg.Absolute stability of global pattern formation and parallel memory storage by competitive neural networks,IEEE Trans on Syst,Man,Cybern,1983,SMC-13(5):815-526.[5]王松桂,贾忠贞、矩阵论中不等式,合肥,安徽教育出版社,1994,第四章.[6]段广仁,线性系统理论,哈尔滨,哈尔滨工业大学出版社, 1996:第三章,第五章.
计量
- 文章访问数: 2088
- HTML全文浏览量: 126
- PDF下载量: 360
- 被引次数: 0