| 基于精确罚函数的一类广义非线性神经网络模型 |
| |
| 引用本文： | 孟志青,胡奇英,杨晓琪.基于精确罚函数的一类广义非线性神经网络模型[J].自动化学报,2003,29(5):755-760. |
| |
| 作者姓名： | 孟志青 胡奇英 杨晓琪 |
| |
| 作者单位： | 1.西安电子科技大学经济管理学院,西安; |
| |
| 基金项目： | 国家自然科学基金 (6 990 4 0 0 8)资助~~ |
| |
| 摘 要： | 针对一般的非线性优化问题定义了一种2次非线性罚函数,证明了在一定条件下对
应的罚优化问题的精确罚定理,由此引进了一种广义非线性神经网络模型,并证明了这种网络
的平衡点与能量函数之间的联系,在一定条件下对应的平衡点收敛到原问题的最优解.这种神
经网络模型对于求解许多优化问题具有重要的作用.
|
| 关 键 词： | 神经网络 非线性罚函数 最优解 平衡点 稳定点 |
| 收稿时间： | 2001-4-11 |
| 修稿时间： | 2001年4月11日 |
A General Model of Non-Linear Neural Networks Based on Exact Penalty Function |
| |
| MENG Zhi-Qing,HU Qi-Ying,YANG Xiao-Qi.A General Model of Non-Linear Neural Networks Based on Exact Penalty Function[J].Acta Automatica Sinica,2003,29(5):755-760. |
| |
| Authors: | MENG Zhi-Qing HU Qi-Ying YANG Xiao-Qi |
| |
| Affiliation: | 1.School of Economics and Management,Xidian University,Xi'an;Department of Applied Mathematics,The Hong Kong Polytechnic University,Hong Kong |
| |
| Abstract: | A double non-linear penalty function is defined for the non-linear optimality problems (NP) and the exact penalty theorem is exacted under some conditions. A new general model of non-linear neural networks is introduced and the relationship between the equilibrium points and the energy function is showed. Under the given condition, the equilibrium point of the neural networks converges to a solution of NP. This model plays an important part in many optimal problems. |
| |
| Keywords: | Neural networks non-linear penalty function optimal solution equilibrium point stable point |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
