文献类型：期刊文献

英文题名：Reformative Noise-Immune Neural Network for Equality-Constrained Optimization Applied to Image Target Detection

作者：Ying Liufu[1,2];Jin, Long[2,3];Xu, Jinqiang[4];Xiao, Xiuchun[4];Fu, Dongyang[4]

机构：[1]Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Gansu, Peoples R China;[2]Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing 100049, Peoples R China;[3]Lanzhou Univ, Dept Comp Sci, Lanzhou 730000, Gansu, Peoples R China;[4]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524088, Guangdong, Peoples R China

年份：2022

卷号：10

期号：2

起止页码：973

外文期刊名：IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING

收录：SCI-EXPANDED(收录号：WOS:000808083300036)、、EI(收录号：20210809935775)、Scopus(收录号：2-s2.0-85100852023)、WOS

基金：This work was supported by the National Key Research and Development Program of China under Grant 2017YFE0118900, by the research project of Huawei Mindspore Academic Award Fund of Chinese Association of Artificial Intelligence CAAIXSJLJJ-2020-009A, by the Team Project of Natural Science Foundation of Qinghai Province, China (No. 2020-ZJ-903), by the Key Laboratory of IoT of Qinghai (No. 2020-ZJ-Y16), by the Natural Science Foundation of Gansu Province, China, under Grant 20JR10RA639, by the Natural Science Foundation of Chongqing (China) under Grant cstc2020jcyj-zdxmX0028, by the Research and Development Foundation of Nanchong (China) under Grant 20YFZJ0018, by CAS "Light of West China" Program, and by Chongqing Key Laboratory of Mobile Communications Technology under Grant cqupt-mct-202004. (Ying Liufu and Long Jin are co-first authors.)

语种：英文

外文关键词：Optimization; Computational modeling; Mathematical model; Numerical models; Convergence; Neural networks; Robustness; Reformative noise-immune neural network (RNINN); equality-constrained optimization; noise-resistance; robustness

外文摘要：Equality-constrained optimization problem captures increasing attention in the fields of computer science, control engineering, and applied mathematics. Almost all of the relevant issues suffer from kinds of intense or weak noises during the solving process, so that how to realize the noise deduction even noise elimination has increasingly become a sticky and significant problem. A lot of corresponding solving models are established for the equality-constrained optimization problem. However, the majority of them can find the optimal solution to a certain extent in the absence of noise disturbance, but few can behave a brilliant noise-resistance proficiency. On account of this discovery, a reformative noise-immune neural network (RNINN) model is constructed. In addition, the conventional gradient-based recursive neural network model and the zeroing recursive neural network model are presented to compare with the proposed RNINN model on convergence properties and noise-resistance capabilities. Lastly, the relative numerical experiment simulation and image target detection application are implemented to further elaborate on the robustness and efficiency of the RNINN model.