{"title":"模糊神经汉明分类器的设计与训练","authors":"Q. Hua, Q.-L. Zhen","doi":"10.1109/ISMVL.2001.924595","DOIUrl":null,"url":null,"abstract":"The Fuzzy Neural Hamming Classifier (FNHC) can resolve the pattern overlap with the degree of fuzzy class membership; ensure the convergence and decrease the interconnection with the comparison subnet; accept both binary and non-binary input. Using only integer threshold and weights, FNHC is easily implemented in VLSI technology.","PeriodicalId":297353,"journal":{"name":"Proceedings 31st IEEE International Symposium on Multiple-Valued Logic","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The designing and training of a fuzzy neural Hamming classifier\",\"authors\":\"Q. Hua, Q.-L. Zhen\",\"doi\":\"10.1109/ISMVL.2001.924595\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Fuzzy Neural Hamming Classifier (FNHC) can resolve the pattern overlap with the degree of fuzzy class membership; ensure the convergence and decrease the interconnection with the comparison subnet; accept both binary and non-binary input. Using only integer threshold and weights, FNHC is easily implemented in VLSI technology.\",\"PeriodicalId\":297353,\"journal\":{\"name\":\"Proceedings 31st IEEE International Symposium on Multiple-Valued Logic\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2001-05-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings 31st IEEE International Symposium on Multiple-Valued Logic\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISMVL.2001.924595\",\"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 31st IEEE International Symposium on Multiple-Valued Logic","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISMVL.2001.924595","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The designing and training of a fuzzy neural Hamming classifier
The Fuzzy Neural Hamming Classifier (FNHC) can resolve the pattern overlap with the degree of fuzzy class membership; ensure the convergence and decrease the interconnection with the comparison subnet; accept both binary and non-binary input. Using only integer threshold and weights, FNHC is easily implemented in VLSI technology.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
