文献类型：期刊文献

英文题名：Robust neural dynamics with adaptive coefficient applied to solve the dynamic matrix square root

作者：Jiang, Chengze[1];Wu, Chaomin[1];Xiao, Xiuchun[1];Lin, Cong[1]

机构：[1]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524088, Peoples R China

年份：2023

卷号：9

期号：4

起止页码：4213

外文期刊名：COMPLEX & INTELLIGENT SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:000904046900004)、、Scopus(收录号：2-s2.0-85144847207)、WOS

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62272109, in part by Nat-ural Science Foundation of Guangdong Province, China under Grant 2021A1515011847, in part by the Special Project in Key Fields of Uni-versities in Department of Education of Guangdong Province under Grant 2019KZDZX1036, in part by the Key Lab of Digital Signal andImage Processing of Guangdong Province under Grant 2019GDDSIPL-01, in part by the Demonstration Bases for Joint Training of Postgrad-uates of Department of Education of Guangdong Province under Grant 202205, in part by Postgraduate Education Innovation Plan Project of Guangdong Ocean University under Grant 202214, in part by the Inno-vation and Entrepreneurship Training Program for College Students of Guangdong Ocean

语种：英文

外文关键词：Dynamic matrix square root; Time-dependent; Zeroing neural network; Adaption coefficient

外文摘要：Zeroing neural networks (ZNN) have shown their state-of-the-art performance on dynamic problems. However, ZNNs are vulnerable to perturbations, which causes reliability concerns in these models owing to the potentially severe consequences. Although it has been reported that some models possess enhanced robustness but cost worse convergence speed. In order to address these problems, a robust neural dynamic with an adaptive coefficient (RNDAC) model is proposed, aided by the novel adaptive activation function and robust evolution formula to boost convergence speed and preserve robustness accuracy. In order to validate and analyze the performance of the RNDAC model, it is applied to solve the dynamic matrix square root (DMSR) problem. Related experiment results show that the RNDAC model reliably solves the DMSR question perturbed by various noises. Using the RNDAC model, we are able to reduce the residual error from 10(1) to 10(-4) with noise perturbed and reached a satisfying and competitive convergence speed, which converges within 3 s.