Evgeny A. Smirnov, Denis M. Timoshenko, Serge N. Andrianov
{"title":"Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks","authors":"Evgeny A. Smirnov, Denis M. Timoshenko, Serge N. Andrianov","doi":"10.1016/j.aasri.2014.05.013","DOIUrl":null,"url":null,"abstract":"<div><p>Large and Deep Convolutional Neural Networks achieve good results in image classification tasks, but they need methods to prevent overfitting. In this paper we compare performance of different regularization techniques on ImageNet Large Scale Visual Recognition Challenge 2013. We show empirically that Dropout works better than DropConnect on ImageNet dataset.</p></div>","PeriodicalId":100008,"journal":{"name":"AASRI Procedia","volume":"6 ","pages":"Pages 89-94"},"PeriodicalIF":0.0000,"publicationDate":"2014-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.aasri.2014.05.013","citationCount":"166","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AASRI Procedia","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212671614000146","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 166
Abstract
Large and Deep Convolutional Neural Networks achieve good results in image classification tasks, but they need methods to prevent overfitting. In this paper we compare performance of different regularization techniques on ImageNet Large Scale Visual Recognition Challenge 2013. We show empirically that Dropout works better than DropConnect on ImageNet dataset.