神经网络训练的亚梯度迭代法

Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems Pub Date : 2011-11-10 DOI:10.1109/IDAACS.2011.6072774

G. Shcherbakova, V. Krylov, Valentin Abakumov, V. Brovkov, I. Kozina

{"title":"神经网络训练的亚梯度迭代法","authors":"G. Shcherbakova, V. Krylov, Valentin Abakumov, V. Brovkov, I. Kozina","doi":"10.1109/IDAACS.2011.6072774","DOIUrl":null,"url":null,"abstract":"Sub gradient iterative method in the wavelet transformed domain for neural networks training rule is proposed. This method allows to improve noise stability, to reduce local extreme and initial point search sensitiveness.","PeriodicalId":106306,"journal":{"name":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Sub gradient iterative method for neural networks training\",\"authors\":\"G. Shcherbakova, V. Krylov, Valentin Abakumov, V. Brovkov, I. Kozina\",\"doi\":\"10.1109/IDAACS.2011.6072774\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Sub gradient iterative method in the wavelet transformed domain for neural networks training rule is proposed. This method allows to improve noise stability, to reduce local extreme and initial point search sensitiveness.\",\"PeriodicalId\":106306,\"journal\":{\"name\":\"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-11-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IDAACS.2011.6072774\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IDAACS.2011.6072774","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

提出了小波变换域下神经网络训练规则的次梯度迭代法。该方法提高了噪声稳定性，降低了局部极值和初始点搜索的灵敏度。

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

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Sub gradient iterative method for neural networks training

Sub gradient iterative method in the wavelet transformed domain for neural networks training rule is proposed. This method allows to improve noise stability, to reduce local extreme and initial point search sensitiveness.

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

Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems

自引率

0.00%

发文量