| An Adaptive Neural Network Model for Nonlinear Programming Problems |
| |
| 作者姓名： | Xiang-sun Zhang Xin-jian Zhuo Zhu-jun JingAcademy of Mathematics and System Sciences Chinese Academy of Sciences Beijing ChinaSchool of Information Engineering Beijing University of Posts and Telecommunications Beijing ChinaHunan Normal University Changsha China & Academy of Mathematics and System Sciences Chinese Academy of Sciences Beijing China |
| |
| 作者单位： | Xiang-sun Zhang，Xin-jian Zhuo，Zhu-jun JingAcademy of Mathematics and System Sciences，Chinese Academy of Sciences，Beijing 100080，ChinaSchool of Information Engineering，Beijing University of Posts and Telecommunications，Beijing 100876，ChinaHunan Normal University，Changsha 410081，China & Academy of Mathematics and System Sciences，Chinese Academy of Sciences，Beijing 100080，China |
| |
| 基金项目： | the the Innovation Fund of the Academy of Mathematics and System Sciences，by the Management,Decision and Information System Lab.,Chinese Academy of Sciences. |
| |
| 摘 要： | In this paper a canonical neural network with adaptively changing synaptic weights and activation function parameters is presented to solve general nonlinear programming problems. The basic part of the model is a sub-network used to find a solution of quadratic programming problems with simple upper and lower bounds. By sequentially activating the sub-network under the control of an external computer or a special analog or digital processor that adjusts the weights and parameters, one then solves general nonlinear programming problems. Convergence proof and numerical results are given.
|
An Adaptive Neural Network Model for Nonlinear Programming Problems |
| |
| Xiang-sun Zhang,Xin-jian Zhuo,Zhu-jun JingAcademy of Mathematics and System Sciences,Chinese Academy of Sciences,Beijing ,ChinaSchool of Information Engineering,Beijing University of Posts and Telecommunications,Beijing ,ChinaHunan Normal University,Changsha ,China & Academy of Mathematics and System Sciences,Chinese Academy of Sciences,Beijing ,China.An Adaptive Neural Network Model for Nonlinear Programming Problems[J].Acta Mathematicae Applicatae Sinica,2002,18(3):377-388. |
| |
| Authors: | Xiang-sun Zhang Xin-jian Zhuo Zhu-jun Jing |
| |
| Institution: | (1) Academy of Mathematics and System Sciences, Chinese Academy of Sciences, Beijing 100080, China (E-mail: zxs@mail.amt.ac.cn), CN;(2) School of Information Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China (E-mail: zhuoxj@mail.bupt.edu.cn), CN;(3) Hunan Normal University, Changsha 410081, China & Academy of Mathematics and System Sciences, Chinese Academy of Sciences, Beijing 100080, China (E-mail: jingzj@math03.math.ac.cn), CN |
| |
| Abstract: | In this paper a canonical neural network with adaptively changing synaptic weights and activation function parameters is presented to solve general nonlinear programming problems. The basic part of the model is a sub-network used to find a solution of quadratic programming problems with simple upper and lower bounds. By sequentially activating the sub-network under the control of an external computer or a special analog or digital processor that adjusts the weights and parameters, one then solves general nonlinear programming problems. Convergence proof and numerical results are given. |
| |
| Keywords: | Adaptive neural network canonical neural network general nonlinear programming |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
