{"title":"Temporal Optical Neurons For Serial Deep Learning","authors":"Ming Li, Zhixing Lin, X. Meng","doi":"10.1109/SUM48717.2021.9505925","DOIUrl":null,"url":null,"abstract":"We propose a three-layer serial optical neural network based on the time-domain Talbot effect for the two-class recognition of English letters “u” & “c” and “a” & “s”, and the recognition accuracy rate reached 100% theoretically.","PeriodicalId":359978,"journal":{"name":"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Photonics Society Summer Topicals Meeting Series (SUM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SUM48717.2021.9505925","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
We propose a three-layer serial optical neural network based on the time-domain Talbot effect for the two-class recognition of English letters “u” & “c” and “a” & “s”, and the recognition accuracy rate reached 100% theoretically.