A Recurrent Neural Network for Solving a Class of General Variational Inequalities

A Recurrent Neural Network for Solving a Class of General Variational Inequalities
复制标题

DOI：
10.1109/tsmcb.2006.886166
复制
发表时间：
2007-06
期刊：
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
影响因子：
--
通讯作者：
Xiaolin Hu;Jun Wang
Xiaolin Hu;Jun Wang
中科院分区：
其他
文献类型：
--
作者：
Xiaolin Hu;Jun Wang

文献摘要

被引文献

相似文献

本文提出了一种递归神经网络模型，用于求解一类特殊的广义变分不等式（GVIs），其中经典变分不等式是其特殊情况。证明了所提出的用于求解这类GVIs的神经网络在不同条件下可以是全局收敛的、全局渐近稳定的以及全局指数稳定的。所提出的神经网络可被视为文献中已有的一般投影神经网络的改进版本。提供了几个数值例子以证明所提出神经网络的有效性和性能。
This paper presents a recurrent neural-network model for solving a special class of general variational inequalities (GVIs), which includes classical VIs as special cases. It is proved that the proposed neural network (NN) for solving this class of GVIs can be globally convergent, globally asymptotically stable, and globally exponentially stable under different conditions. The proposed NN can be viewed as a modified version of the general projection NN existing in the literature. Several numerical examples are provided to demonstrate the effectiveness and performance of the proposed NN