| LOGICAL ANALYSIS FOR NEURAL NETWORKS |
| |
| 引用本文： | Guo Baolong(Department of Detection and Instrument,Xidian University,Xi'an 710071)Guo Lei(Department of Automatic Control,Northwest Polytechnic University,Xi'an 710072). LOGICAL ANALYSIS FOR NEURAL NETWORKS[J]. 电子科学学刊(英文版), 1997, 14(2): 117-124. DOI: 10.1007/s11767-997-1003-7 |
| |
| 作者姓名： | Guo Baolong(Department of Detection and Instrument Xidian University Xi'an 710071)Guo Lei(Department of Automatic Control Northwest Polytechnic University Xi'an 710072) |
| |
| 作者单位： | Guo Baolong(Department of Detection and Instrument，Xidian University，Xi'an 710071)Guo Lei(Department of Automatic Control，Northwest Polytechnic University，Xi'an 710072) |
| |
| 基金项目： | 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.
|
Logical analysis for neural networks |
| |
| Guo Baolong,Guo Lei. Logical analysis for neural networks[J]. Journal of Electronics, 1997, 14(2): 117-124. DOI: 10.1007/s11767-997-1003-7 |
| |
| Authors: | Guo Baolong Guo Lei |
| |
| Affiliation: | (1) Department of Detection and Instrument, Xidian University, 710071 Xi’an;(2) Department of Automatic Control, Northwest Polytechnic University, 710072 Xi’an |
| |
| Abstract: | 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. |
| |
| Keywords: | Neural networks Constraint satisfaction networks Inference Contradiction analysis |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
| 点击此处可从《电子科学学刊(英文版)》浏览原始摘要信息 |
|
点击此处可从《电子科学学刊(英文版)》下载全文 |
