| 神经网络模型求解约束优化问题的研究 |
| |
| 引用本文： | 任登鸿,张著洪.神经网络模型求解约束优化问题的研究[J].贵州大学学报(自然科学版),2005,22(1):47-50,58. |
| |
| 作者姓名： | 任登鸿 张著洪 |
| |
| 作者单位： | 1. 贵州大学,经济学校,贵州,贵阳,550025
2. 贵州大学,理学院,贵州,贵阳,550025 |
| |
| 摘 要： | 依据罚函数及动态处罚法设计增广Lagrange乘子函数，获得新的神经网络模型解决约束优化问题。理论论证了该模型的稳定性以及在一定条件下网络收敛的平衡点即为所解决的优化问题的最优解。事例仿真论证了该模型处理优化问题的有效性。
|
| 关 键 词： | 神经网络 动态处罚法 最优化 平衡点 |
| 文章编号： | 1000-5269(2005)01-0047-04 |
Study on Neural Network Applied to Constrained Optimization |
| |
| REN Deng-hong,ZHANG Zhu-hong.Study on Neural Network Applied to Constrained Optimization[J].Journal of Guizhou University(Natural Science),2005,22(1):47-50,58. |
| |
| Authors: | REN Deng-hong ZHANG Zhu-hong |
| |
| Institution: | REN Deng-hong1,ZHANG Zhu-hong2 |
| |
| Abstract: | A novel neural network, of which is applied to universal nonlinear constrained optimization, is proposed based dynamical penalty function method and general Lagrange multiply one. Theoretically, its stability is demonstrated, and it converges to the optimal solutions of solved optimization problems under certain conditions. The simulation shows its availability. |
| |
| Keywords: | Neural Network Dynamical penalty method Optimization equilibrium |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
