文献类型：期刊文献

英文题名：Coevolutionary Neural Solution for Nonconvex Optimization With Noise Tolerance

作者：Jin, Long[1];Su, Zeyu[1];Fu, Dongyang[2];Xiao, Xiuchun[2]

机构：[1]Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Peoples R China;[2]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524091, Peoples R China

年份：2024

卷号：35

期号：12

起止页码：17571

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:001373104900034)、、EI(收录号：20233614686615)、Scopus(收录号：2-s2.0-85169681208)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62176109 and Grant 62311530099; in part by the Fundamental Research Funds for the Central Universities under Grant lzujbky-2023-eyt04 and Grant lzujbky-2023-ey07; in part by the CAAI-Huawei MindSpore Open Fund under Grant CAAIXSJLJJ-2022-020A; in part by the Team Project of Natural Science Foundation of Qinghai Province, China, under Grant 2020-ZJ-903; and in part by the Supercomputing Center of Lanzhou University. (Corresponding author: Long Jin.)

语种：英文

外文关键词：Coevolutionary neural solution (CNS); finite impulse response (FIR) filter; neurodynamics model; noise tolerance

外文摘要：The existing solutions for nonconvex optimization problems show satisfactory performance in noise-free scenarios. However, they are prone to yield inaccurate results in the presence of noise in real-world problems, which may lead to failures in optimizing nonconvex problems. To this end, in this article, we propose a coevolutionary neural solution (CNS) by combining a simplified neurodynamics (SND) model with the particle swarm optimization (PSO) algorithm. Specifically, the proposed SND model does not leverage the time-derivative information, exhibiting greater stability compared to existing models. Furthermore, due to the noise tolerance capacity and rapid convergence property exhibited by the SND model, the CNS can rapidly achieve the optimal solution even in the presence of various perturbations. Theoretical analyses ensure that the proposed CNS is globally convergent with robustness and probability. In addition, the effectiveness of the CNS is compared with those of the existing solutions by a class of illustrative examples. We further apply the proposed solution to design a finite impulse response (FIR) filter and a pressure vessel to demonstrate its performance.