深度神经网络的进化构建算法

2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM) Pub Date : 2017-06-28 DOI:10.1109/WSOM.2017.8020002

R. Zemouri

{"title":"深度神经网络的进化构建算法","authors":"R. Zemouri","doi":"10.1109/WSOM.2017.8020002","DOIUrl":null,"url":null,"abstract":"The increase of the computer power has contributed significantly to the development of the Deep Neural Networks. However, the training phase is more difficult since there are many hidden layers with many connections. The aim of this paper is to improve the learning procedure for Deep Neural Networks. A new method for building an evolutionary DNN is presented. With our method, the user does not have to arbitrary specify the number of hidden layers nor the number of neurons per layer. Illustrative examples are provided to support the theoretical analysis.","PeriodicalId":130086,"journal":{"name":"2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"An evolutionary building algorithm for Deep Neural Networks\",\"authors\":\"R. Zemouri\",\"doi\":\"10.1109/WSOM.2017.8020002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The increase of the computer power has contributed significantly to the development of the Deep Neural Networks. However, the training phase is more difficult since there are many hidden layers with many connections. The aim of this paper is to improve the learning procedure for Deep Neural Networks. A new method for building an evolutionary DNN is presented. With our method, the user does not have to arbitrary specify the number of hidden layers nor the number of neurons per layer. Illustrative examples are provided to support the theoretical analysis.\",\"PeriodicalId\":130086,\"journal\":{\"name\":\"2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WSOM.2017.8020002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WSOM.2017.8020002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

摘要

计算机性能的提高为深度神经网络的发展做出了重要贡献。然而，训练阶段更加困难，因为有许多隐藏层和许多连接。本文的目的是改进深度神经网络的学习过程。提出了一种构建进化深度神经网络的新方法。使用我们的方法，用户不必任意指定隐藏层的数量或每层神经元的数量。并提供了实例来支持理论分析。

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

An evolutionary building algorithm for Deep Neural Networks

The increase of the computer power has contributed significantly to the development of the Deep Neural Networks. However, the training phase is more difficult since there are many hidden layers with many connections. The aim of this paper is to improve the learning procedure for Deep Neural Networks. A new method for building an evolutionary DNN is presented. With our method, the user does not have to arbitrary specify the number of hidden layers nor the number of neurons per layer. Illustrative examples are provided to support the theoretical analysis.

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

2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM)

自引率

0.00%

发文量