{"title":"在输入的几何变换下构造具有期望行为的神经结构","authors":"V. Dudar, V. Semenov","doi":"10.17721/2706-9699.2020.1.03","DOIUrl":null,"url":null,"abstract":"We present a general method for analysis of convolutional layers under geometric transformations of the input that are linear with respect to pixel values. We also describe the algorithm for finding all possible types of behaviours of the output of convolutional layers under geometric transformations of the input. We also present a general method for construction of convolutional architectures with desired behaviour under geometric transformations of the input.","PeriodicalId":40347,"journal":{"name":"Journal of Numerical and Applied Mathematics","volume":"35 1","pages":""},"PeriodicalIF":0.1000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT\",\"authors\":\"V. Dudar, V. Semenov\",\"doi\":\"10.17721/2706-9699.2020.1.03\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a general method for analysis of convolutional layers under geometric transformations of the input that are linear with respect to pixel values. We also describe the algorithm for finding all possible types of behaviours of the output of convolutional layers under geometric transformations of the input. We also present a general method for construction of convolutional architectures with desired behaviour under geometric transformations of the input.\",\"PeriodicalId\":40347,\"journal\":{\"name\":\"Journal of Numerical and Applied Mathematics\",\"volume\":\"35 1\",\"pages\":\"\"},\"PeriodicalIF\":0.1000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Numerical and Applied Mathematics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.17721/2706-9699.2020.1.03\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Numerical and Applied Mathematics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.17721/2706-9699.2020.1.03","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
CONSTRUCTION OF NEURAL ARCHITECTURES WITH DESIRED BEHAVIOUR UNDER GEOMETRIC TRANSFORMATIONS OF THE INPUT
We present a general method for analysis of convolutional layers under geometric transformations of the input that are linear with respect to pixel values. We also describe the algorithm for finding all possible types of behaviours of the output of convolutional layers under geometric transformations of the input. We also present a general method for construction of convolutional architectures with desired behaviour under geometric transformations of the input.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
