Altai Perry, Xiaojing Weng, Baurzhan Muminov, L. Vuong
{"title":"SVD Entropy Indicates Coded Diffraction Generalized Reconstruction Accuracy","authors":"Altai Perry, Xiaojing Weng, Baurzhan Muminov, L. Vuong","doi":"10.1364/cosi.2022.cf2c.2","DOIUrl":null,"url":null,"abstract":"We study encoded diffraction with shallow neural networks using singular value decomposition entropy (H\n SVD\n ) to measure image span. Higher-H\n SVD\n synthetic training images are learned more slowly; their generalized models generally attain higher reconstruction accuracy.","PeriodicalId":286361,"journal":{"name":"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Imaging and Applied Optics Congress 2022 (3D, AOA, COSI, ISA, pcAOP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/cosi.2022.cf2c.2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
We study encoded diffraction with shallow neural networks using singular value decomposition entropy (H
SVD
) to measure image span. Higher-H
SVD
synthetic training images are learned more slowly; their generalized models generally attain higher reconstruction accuracy.