解一类变分不等式问题的神经网络

Neural network for a class of variational inequalities

基于射影方法 ,给出了求解一类变分不等式问题的一个神经网络 .该模型结构简单 ,并能全局一致渐近稳定地收敛于原问题的精确解 .最后将该网络应用于最小距离问题 ,并作了模拟实验 ,结果表明该模型是可行的和有效的 .

Based on the projection method, this paper proposes a neural network for solving a class of variational inequalities. Its structure is very simple. It can be guaranteed to be convergent globally, unifomly, asymptotically stably to the exact solution of original problems. Finally, an application of the network to the least distance problem is given, and its feasibility and efficiency are confirmed by numerical experiments.