{"title":"人工神经网络ART-1训练的新算法","authors":"Yu. Rashchenko, V. Kozynchenko","doi":"10.1109/SCP.2015.7342238","DOIUrl":null,"url":null,"abstract":"The paper considers a new algorithm for training of the artificial neural network ART-1, based on simulation of a biosimilar property of short-term memory. A modified neural network is realized as a computer model, comparative testing of classical and modified networks is carried out, its results are analyzed.","PeriodicalId":110366,"journal":{"name":"2015 International Conference \"Stability and Control Processes\" in Memory of V.I. Zubov (SCP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"New algorithms of an artificial neural network ART-1 training\",\"authors\":\"Yu. Rashchenko, V. Kozynchenko\",\"doi\":\"10.1109/SCP.2015.7342238\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper considers a new algorithm for training of the artificial neural network ART-1, based on simulation of a biosimilar property of short-term memory. A modified neural network is realized as a computer model, comparative testing of classical and modified networks is carried out, its results are analyzed.\",\"PeriodicalId\":110366,\"journal\":{\"name\":\"2015 International Conference \\\"Stability and Control Processes\\\" in Memory of V.I. Zubov (SCP)\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-12-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 International Conference \\\"Stability and Control Processes\\\" in Memory of V.I. Zubov (SCP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SCP.2015.7342238\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference \"Stability and Control Processes\" in Memory of V.I. Zubov (SCP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SCP.2015.7342238","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
New algorithms of an artificial neural network ART-1 training
The paper considers a new algorithm for training of the artificial neural network ART-1, based on simulation of a biosimilar property of short-term memory. A modified neural network is realized as a computer model, comparative testing of classical and modified networks is carried out, its results are analyzed.