一种解决非光滑非凸优化问题的暂态混沌神经网络  

Transient Chaotic Neural Network for Nonsmooth and Nonconvex Optimization Problems

作　　者：喻昕[1] 汪炎林 徐柳明 伍灵贞 YU Xin;WANG Yan-lin;XU Liu-ming;WU Ling-zhen(Department of Computer and Electronic Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《小型微型计算机系统》2020年第12期2522-2528,共7页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61862004)资助。

摘　　要：提出了一个新的递归神经网络模型,目标是解决一类带等式与不等式约束的非光滑非凸优化问题.证明了当可行域有界时,递归神经网络能在有限时间内收敛到可行域,并且能最终收敛到优化问题的一个关键点.并针对一般的递归神经网络在解决非凸优化问题过程中容易陷入局部最优解的情况,本文的递归神经网络扩展为暂态混沌神经网络,能通过混沌遍历收敛到优化问题的全局最优点.最终通过实验验证了提出模型的有效性和全局寻优能力.A new recurrent neural network model is proposed to solve a class of nonsmooth nonconvex optimization problems with equality and inequality constraints It is proved that w hen the feasible region is bounded,the recurrent neural network can converge to the feasible region in finite time and finally to a key point of the optimization problem.For the general recurrent neural network is easy to fall into the local optimal solution in the process of solving the nonconvex optimization problem,the recurrent neural network in this paper is extended to the transient chaotic neural network,w hich can converge to the global optimal solution of the optimization problem through chaotic ergodic.Finally,the effectiveness and global optimization ability of the proposed model are verified by experiments.

关 键 词：神经网络 非凸优化问题 暂态混沌神经网络 最优解 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]