{"title":"高阶矩神经网络计算性能研究","authors":"W.A. Porter, W. Liu","doi":"10.1016/1069-0115(94)00041-Y","DOIUrl":null,"url":null,"abstract":"<div><p>Four benchmark examples for evaluating neural network performance are considered. The performance of the higher order moment neural array, HOMNA, on these benchmarks is explored. Comparable results for backprop networks and ARTMAP networks are available in the literature. It is shown that HOMNA trains faster and gives equivalent or better performance than either of these two alternative neural formats.</p></div>","PeriodicalId":100668,"journal":{"name":"Information Sciences - Applications","volume":"3 3","pages":"Pages 179-191"},"PeriodicalIF":0.0000,"publicationDate":"1995-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/1069-0115(94)00041-Y","citationCount":"6","resultStr":"{\"title\":\"On the performance of higher order moment neural computation\",\"authors\":\"W.A. Porter, W. Liu\",\"doi\":\"10.1016/1069-0115(94)00041-Y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Four benchmark examples for evaluating neural network performance are considered. The performance of the higher order moment neural array, HOMNA, on these benchmarks is explored. Comparable results for backprop networks and ARTMAP networks are available in the literature. It is shown that HOMNA trains faster and gives equivalent or better performance than either of these two alternative neural formats.</p></div>\",\"PeriodicalId\":100668,\"journal\":{\"name\":\"Information Sciences - Applications\",\"volume\":\"3 3\",\"pages\":\"Pages 179-191\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1995-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/1069-0115(94)00041-Y\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information Sciences - Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/106901159400041Y\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Sciences - Applications","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/106901159400041Y","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
On the performance of higher order moment neural computation
Four benchmark examples for evaluating neural network performance are considered. The performance of the higher order moment neural array, HOMNA, on these benchmarks is explored. Comparable results for backprop networks and ARTMAP networks are available in the literature. It is shown that HOMNA trains faster and gives equivalent or better performance than either of these two alternative neural formats.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
