{"title":"线性输出神经网络循环Dropconnect反向传播算法的确定性收敛性","authors":"Junling Jing, Zaiqiang Wang, Huisheng Zhang","doi":"10.1109/WCCCT56755.2023.10052295","DOIUrl":null,"url":null,"abstract":"In this paper, we consider the backpropagation algorithm with cyclic DropConnect (BPA-CDC) for neural networks with linear output. Under mild conditions, we establish the deterministic convergence theory for BPA-CDC, showing that the cost function tends to a constant, the gradient tends to zero, and the weight vector tends to a point. Simulation results are provided to validate our theoretical findings.","PeriodicalId":112978,"journal":{"name":"2023 6th World Conference on Computing and Communication Technologies (WCCCT)","volume":"37 6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deterministic Convergence of Backpropagation Algorithm with Cyclic Dropconnect for Linear Output Neural Networks\",\"authors\":\"Junling Jing, Zaiqiang Wang, Huisheng Zhang\",\"doi\":\"10.1109/WCCCT56755.2023.10052295\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we consider the backpropagation algorithm with cyclic DropConnect (BPA-CDC) for neural networks with linear output. Under mild conditions, we establish the deterministic convergence theory for BPA-CDC, showing that the cost function tends to a constant, the gradient tends to zero, and the weight vector tends to a point. Simulation results are provided to validate our theoretical findings.\",\"PeriodicalId\":112978,\"journal\":{\"name\":\"2023 6th World Conference on Computing and Communication Technologies (WCCCT)\",\"volume\":\"37 6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 6th World Conference on Computing and Communication Technologies (WCCCT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WCCCT56755.2023.10052295\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 6th World Conference on Computing and Communication Technologies (WCCCT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WCCCT56755.2023.10052295","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deterministic Convergence of Backpropagation Algorithm with Cyclic Dropconnect for Linear Output Neural Networks
In this paper, we consider the backpropagation algorithm with cyclic DropConnect (BPA-CDC) for neural networks with linear output. Under mild conditions, we establish the deterministic convergence theory for BPA-CDC, showing that the cost function tends to a constant, the gradient tends to zero, and the weight vector tends to a point. Simulation results are provided to validate our theoretical findings.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
