Ian A. D. Williamson, Tyler W. Hughes, M. Minkov, S. Fan
{"title":"非线性光波的循环机器学习与计算","authors":"Ian A. D. Williamson, Tyler W. Hughes, M. Minkov, S. Fan","doi":"10.1364/cleo_qels.2020.fw4b.1","DOIUrl":null,"url":null,"abstract":"We demonstrate that optical time-dynamics are equivalent to a recurrent neural network and that they can be trained for high-performance on complex classification tasks, paving the way for passive analog machine learning processors.","PeriodicalId":6719,"journal":{"name":"2020 Conference on Lasers and Electro-Optics (CLEO)","volume":"43 1","pages":"1-2"},"PeriodicalIF":0.0000,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Recurrent Machine Learning and Computing with Nonlinear Optical Waves\",\"authors\":\"Ian A. D. Williamson, Tyler W. Hughes, M. Minkov, S. Fan\",\"doi\":\"10.1364/cleo_qels.2020.fw4b.1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We demonstrate that optical time-dynamics are equivalent to a recurrent neural network and that they can be trained for high-performance on complex classification tasks, paving the way for passive analog machine learning processors.\",\"PeriodicalId\":6719,\"journal\":{\"name\":\"2020 Conference on Lasers and Electro-Optics (CLEO)\",\"volume\":\"43 1\",\"pages\":\"1-2\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Conference on Lasers and Electro-Optics (CLEO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1364/cleo_qels.2020.fw4b.1\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Conference on Lasers and Electro-Optics (CLEO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/cleo_qels.2020.fw4b.1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Recurrent Machine Learning and Computing with Nonlinear Optical Waves
We demonstrate that optical time-dynamics are equivalent to a recurrent neural network and that they can be trained for high-performance on complex classification tasks, paving the way for passive analog machine learning processors.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
