LOGICAL ANALYSIS FOR NEURAL NETWORKS  

作　　者：Guo Baolong(Department of Detection and Instrument, Xidian University, Xi’an 710071)Guo Lei(Department of Automatic Control, Northwest Polytechnic University, Xi’an 710072) 

出　　处：《Journal of Electronics(China)》1997年第2期117-124,共8页电子科学学刊（英文版）

基　　金：Supported by the National Natural Science Foundation of China;the National Hightech Project of China(863)

摘　　要：By comparison with constraint satisfaction networks, this paper presents an essential frame of the logical theory for continuous-state neural networks, and gives the quantitative analyzing method for contradiction. The analysis indicates that the basic reason for the alternation of the logical states of the neurons is the existence of superior contradiction inside the networks. The dynamic process for a neural network to find a solution corresponds to eliminating the superior contradiction.By comparison with constraint satisfaction networks, this paper presents an essential frame of the logical theory for continuous-state neural networks, and gives the quantitative analyzing method for contradiction. The analysis indicates that the basic reason for the alternation of the logical states of the neurons is the existence of superior contradiction inside the networks. The dynamic process for a neural network to find a solution corresponds to eliminating the superior contradiction.

关 键 词：NEURAL NETWORKS CONSTRAINT SATISFACTION NETWORKS INFERENCE CONTRADICTION analysis 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]