| 求解一类线性变分不等式的一个射影神经网络 |
| |
| 引用本文： | 王婧,高兴宝,毕红梅. 求解一类线性变分不等式的一个射影神经网络[J]. 济南大学学报(自然科学版), 2007, 21(1): 82-85 |
| |
| 作者姓名： | 王婧 高兴宝 毕红梅 |
| |
| 作者单位： | 陕西师范大学,数学与信息科学学院,陕西,西安,710062;陕西师范大学,数学与信息科学学院,陕西,西安,710062;陕西师范大学,数学与信息科学学院,陕西,西安,710062 |
| |
| 基金项目： | 陕西省自然科学基金;国家自然科学基金 |
| |
| 摘 要： | 考虑了一类线性变分不等式问题，提出了求解它的一个射影神经网络模型，构造恰当的能量函数，给出了确保新模型稳定和有限时间收敛的3个充分条件，并在适当的条件下，证明了该模型的指数稳定性。新模型结构简单，易于硬件实现，可用来求解非单调的问题。数值试验表明该网络不仅有效而且可行。
|
| 关 键 词： | 线性变分不等式 神经网络 指数稳定性 有限时间收敛性 |
| 文章编号： | 1671-3559(2007)01-0082-04 |
| 修稿时间： | 2006-10-31 |
A Projected Neural Network for a Class of Linear Variational Inequalities |
| |
| WANG Jing,GAO Xing-bao,BI Hong-mei. A Projected Neural Network for a Class of Linear Variational Inequalities[J]. Journal of Jinan University(Science & Technology), 2007, 21(1): 82-85 |
| |
| Authors: | WANG Jing GAO Xing-bao BI Hong-mei |
| |
| Abstract: | This paper considers a class of linear variational inequalities,and presents a projected neural network to solve it.Three sufficient conditions are provided to ensure that the proposed neural network is stable in the sense of lyapunov and has a finite-time convergence by introducing the energy functions.Meanwhile,the global exponential stability of the new model is also shown under some mild conditions.The new model has a lower complexity for parallel implementation,and can be applied to solve some nonmonotone problems.The feasibility and efficiency are confirmed by numerical experiments. |
| |
| Keywords: | linear variational inequality neural network exponential stability finite-time convergence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
