节点文献
求解一类线性变分不等式的一个射影神经网络
A Projected Neural Network for a Class of Linear Variational Inequalities
【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。
【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.
【Key words】 linear variational inequality; neural network; exponential stability; finite-time convergence;
- 【文献出处】 济南大学学报(自然科学版) ,Journal of Jinan University(Science and Technology) , 编辑部邮箱 ,2007年01期
- 【分类号】O221
- 【下载频次】90