基于合成数据的神经网络集成效率分析

2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) Pub Date : 2020-06-01 DOI:10.1109/WECONF48837.2020.9131495

P. Menshih, S. Erokhin, M. Gorodnichev

{"title":"基于合成数据的神经网络集成效率分析","authors":"P. Menshih, S. Erokhin, M. Gorodnichev","doi":"10.1109/WECONF48837.2020.9131495","DOIUrl":null,"url":null,"abstract":"Ensembles of neural networks are used to improve the performance of the model and show themselves well in the case of using deep recurrent and convolutional networks on serial [1] and graphic data [2]. The article discusses the advisability of using a snapshot ensemble of not deep feedforward neural networks on a synthetic dataset.","PeriodicalId":303530,"journal":{"name":"2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Efficiency Analysis of Neural Networks Ensembles Using Synthetic Data\",\"authors\":\"P. Menshih, S. Erokhin, M. Gorodnichev\",\"doi\":\"10.1109/WECONF48837.2020.9131495\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Ensembles of neural networks are used to improve the performance of the model and show themselves well in the case of using deep recurrent and convolutional networks on serial [1] and graphic data [2]. The article discusses the advisability of using a snapshot ensemble of not deep feedforward neural networks on a synthetic dataset.\",\"PeriodicalId\":303530,\"journal\":{\"name\":\"2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WECONF48837.2020.9131495\",\"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 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WECONF48837.2020.9131495","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

神经网络的集成用于提高模型的性能，并在对序列[1]和图形数据[2]使用深度循环和卷积网络的情况下表现良好。本文讨论了在合成数据集上使用非深度前馈神经网络的快照集合的可行性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Efficiency Analysis of Neural Networks Ensembles Using Synthetic Data

Ensembles of neural networks are used to improve the performance of the model and show themselves well in the case of using deep recurrent and convolutional networks on serial [1] and graphic data [2]. The article discusses the advisability of using a snapshot ensemble of not deep feedforward neural networks on a synthetic dataset.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)

自引率

0.00%

发文量