{"title":"多层感知器的联合优化方法","authors":"Chen Yongsheng, Liang Biqing, Y. Baozong","doi":"10.1109/TENCON.1993.320126","DOIUrl":null,"url":null,"abstract":"The backpropagation algorithm (BP) is one of the most popular algorithms in neural network studies, but it is notorious for its slowness in achieving convergence. Based on the theory of unconstrained optimization, the union optimization method (UOM) is presented. The method consists of two parts: apply Descent Method to optimize objective function E=/spl Sigmasub p/E/sub p/; when E</spl epsi/, apply conjugate gradient method to optimize objective function. Apply the UOM to train speech pattern, the experiment result shows the convergence speed of UOM is fourteen times faster than conventional BP algorithm.<<ETX>>","PeriodicalId":110496,"journal":{"name":"Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1993-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The union optimization method of multilayer perceptron\",\"authors\":\"Chen Yongsheng, Liang Biqing, Y. Baozong\",\"doi\":\"10.1109/TENCON.1993.320126\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The backpropagation algorithm (BP) is one of the most popular algorithms in neural network studies, but it is notorious for its slowness in achieving convergence. Based on the theory of unconstrained optimization, the union optimization method (UOM) is presented. The method consists of two parts: apply Descent Method to optimize objective function E=/spl Sigmasub p/E/sub p/; when E</spl epsi/, apply conjugate gradient method to optimize objective function. Apply the UOM to train speech pattern, the experiment result shows the convergence speed of UOM is fourteen times faster than conventional BP algorithm.<<ETX>>\",\"PeriodicalId\":110496,\"journal\":{\"name\":\"Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1993-10-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TENCON.1993.320126\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TENCON.1993.320126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The union optimization method of multilayer perceptron
The backpropagation algorithm (BP) is one of the most popular algorithms in neural network studies, but it is notorious for its slowness in achieving convergence. Based on the theory of unconstrained optimization, the union optimization method (UOM) is presented. The method consists of two parts: apply Descent Method to optimize objective function E=/spl Sigmasub p/E/sub p/; when E>
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
