{"title":"具有良好泛化的感知器多层人工神经网络","authors":"Tian Yubo, Dong Yue, Zhang Xiaoqiu, Zhu Renjie","doi":"10.1109/ICEAA.2007.4387431","DOIUrl":null,"url":null,"abstract":"Feedforward perceptron multilayer (PML) ANNs with error back propagation learning method is often used in engineering design. Unfortunately, its generalization is often poor. In this paper, some reformative methods are proposed to improve its generalization. Based on the improved PML ANN, E-plane T-kind terminal matched load of rectangular waveguide is designed successfully. The result given by the ANN is agreeable with FDTD very well.","PeriodicalId":273595,"journal":{"name":"2007 International Conference on Electromagnetics in Advanced Applications","volume":"49 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Perceptron Multilayer Artificial Neural Network with Good Generalization\",\"authors\":\"Tian Yubo, Dong Yue, Zhang Xiaoqiu, Zhu Renjie\",\"doi\":\"10.1109/ICEAA.2007.4387431\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Feedforward perceptron multilayer (PML) ANNs with error back propagation learning method is often used in engineering design. Unfortunately, its generalization is often poor. In this paper, some reformative methods are proposed to improve its generalization. Based on the improved PML ANN, E-plane T-kind terminal matched load of rectangular waveguide is designed successfully. The result given by the ANN is agreeable with FDTD very well.\",\"PeriodicalId\":273595,\"journal\":{\"name\":\"2007 International Conference on Electromagnetics in Advanced Applications\",\"volume\":\"49 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 International Conference on Electromagnetics in Advanced Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEAA.2007.4387431\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 International Conference on Electromagnetics in Advanced Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEAA.2007.4387431","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Perceptron Multilayer Artificial Neural Network with Good Generalization
Feedforward perceptron multilayer (PML) ANNs with error back propagation learning method is often used in engineering design. Unfortunately, its generalization is often poor. In this paper, some reformative methods are proposed to improve its generalization. Based on the improved PML ANN, E-plane T-kind terminal matched load of rectangular waveguide is designed successfully. The result given by the ANN is agreeable with FDTD very well.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
