|
|||||
|
|
| 一类求解约束非线性规划问题的神经网络模型 | |
| 引用本文： | 陶卿,刘欣,方廷健. 一类求解约束非线性规划问题的神经网络模型[J]. 生物数学学报, 2000, 15(1): 1-7 |
| 作者姓名： | 陶卿 刘欣 方廷健 |
| 作者单位： | 1. 合肥智能机械研究所中国科学院 230031 2. 合肥炮兵学院理化教研室 230031 |
| 摘 要： | 提出一类求解闭凸集上非线性规划问题的神经网络模型。理论分析和计算机模拟表明在适当的假设下所提出的神经网络模型大范围指数级收敛于非线性规划问题的解集。本文神经网络所采用的方法属于广义的最速下降法，甚至当规划问题地正定二次时，本文的模型也比已有的神经网络模型简单。 |
| 关 键 词： | 神经网络 非线性规划问题 大范围收敛 投影算子 |
| 文章编号： | 1001-9626(2000)01-0001-07 |
| 修稿时间： | 1998-06-18 |
A Kind of Neural Network Model for Nonlinear Programming Problems with Constraints |
|
| Tao Qing,Liu Xin,Fang Tingjian. A Kind of Neural Network Model for Nonlinear Programming Problems with Constraints[J]. Journal of Biomathematics, 2000, 15(1): 1-7 | |
| Authors: | Tao Qing Liu Xin Fang Tingjian |
| Affiliation: | Tao Qing;(He fei Institute of Intelligent Machines, Acadmia Sinica China 230031);Liu Xin;(Teachin and Research Section of Physics and Chemistry,Hefei Artillery Academy 230031);Fang Tingjian;(He fei Institute of Intelligent Machines, Acadmia Sinica China 230031) |
| Abstract: | A kind of neural network model for nonlinear programming problems on a closed convex set is presented in this paper Theoretic analysis and simulation results on the computer show the neural network is globally convergent exponentially to the exact solutions of the programming problems under some appropriate assumptions. The optimization method employed by the neural network falls into the extended gradient method. The model is simpler than the existing neural network models even when it is for positive definite quadratic programming problems. |
| Keywords: | Neural networks Nonlinear programming problems Convergent globally Projection operator |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |