| 用随机神经网络优化求解改进算法的研究 |
| |
| 引用本文： | 王怡雯,丛爽.用随机神经网络优化求解改进算法的研究[J].计算机工程与设计,2004,25(9):1454-1456. |
| |
| 作者姓名： | 王怡雯 丛爽 |
| |
| 作者单位： | 中国科学技术大学,自动化系,安徽,合肥,230027 |
| |
| 基金项目： | 安徽省自然科学基金(03042301) |
| |
| 摘 要： | 随机神经网络是一种仿照实际的生物神经网络的生理机制而定义的网络，其网络结构及应用具有自身的特点。在详细讨论了动态随机神经网络求解典型NP优化问题TSP的算法的同时，特别提出了一种有效改进算法，使得参数在简单选取的情况下保证能量函数的下降，在组合优化问题上具有普遍意义，并且在10城市TSP对改进算法进行验证，指出RNN是解决TSP问题的有效途径。
|
| 关 键 词： | 改进算法 神经网络 TSP问题 RNN 能量函数 随机 NP 组合优化问题 优化求解 选取 |
| 文章编号： | 1000-7024(2004)09-1454-03 |
Improved algorithm research of optimization solution with random neural network |
| |
| WANG Yi-wen,CONG Shuang.Improved algorithm research of optimization solution with random neural network[J].Computer Engineering and Design,2004,25(9):1454-1456. |
| |
| Authors: | WANG Yi-wen CONG Shuang |
| |
| Affiliation: | WANG Yi-wen,CONG Shuang Department of Automation,University of Science and Technology of China,Hefei 230027,China |
| |
| Abstract: | Random neural network is defined according to the actually biologic neural networks. It has its own peculiarities on the
structure and the applications. The algorithm on the typical optimal problems - TSP with dynamical random neural network is elaborated.
Especially,an effective improved algorithm is put foreword. The decline of the energy function is ensured by the simply selected parameter
that has universal significance on combinatorial optimization. The improved algorithm is tested in solving 10-city TSP, and random
neural network is verified to be an effective way to solve TSP. |
| |
| Keywords: | random neural network improved algorithm combinatorial optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
