{"title":"基于patch的地震时间序列深度神经网络训练中的信息理论考虑","authors":"J. Dramsch, M. Lüthje","doi":"10.3997/2214-4609.201803020","DOIUrl":null,"url":null,"abstract":"Summary Recent advances in machine learning relies on convolutional deep neural networks. These are often trained on cropped image patches. Pertaining to non-stationary seismic signals this may introduce low frequency noise and non-generalizability.","PeriodicalId":231338,"journal":{"name":"First EAGE/PESGB Workshop Machine Learning","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Information Theory Considerations In Patch-Based Training Of Deep Neural Networks On Seismic Time-Series\",\"authors\":\"J. Dramsch, M. Lüthje\",\"doi\":\"10.3997/2214-4609.201803020\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Summary Recent advances in machine learning relies on convolutional deep neural networks. These are often trained on cropped image patches. Pertaining to non-stationary seismic signals this may introduce low frequency noise and non-generalizability.\",\"PeriodicalId\":231338,\"journal\":{\"name\":\"First EAGE/PESGB Workshop Machine Learning\",\"volume\":\"37 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"First EAGE/PESGB Workshop Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3997/2214-4609.201803020\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"First EAGE/PESGB Workshop Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3997/2214-4609.201803020","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Information Theory Considerations In Patch-Based Training Of Deep Neural Networks On Seismic Time-Series
Summary Recent advances in machine learning relies on convolutional deep neural networks. These are often trained on cropped image patches. Pertaining to non-stationary seismic signals this may introduce low frequency noise and non-generalizability.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
