基于节点分组的深度神经网络训练与压缩Ising Dropout

H. Salehinejad, Zijian Wang, S. Valaee
{"title":"基于节点分组的深度神经网络训练与压缩Ising Dropout","authors":"H. Salehinejad, Zijian Wang, S. Valaee","doi":"10.1109/GlobalSIP45357.2019.8969121","DOIUrl":null,"url":null,"abstract":"Dropout is a popular regularization method to reduce over-fitting while training deep neural networks and compress the inference model. In this paper, we propose Ising dropout with node grouping, which represents a deep multilayer perceptron (MLP) neural network as a graph with fixed grouped nodes and uses the Ising energy to drop group of nodes. This method is an extension to our proposed Ising dropout method, which had the limit of solving the Ising energy model for MLPs with limited graph order. The proposed fixed grouping method enables applying drop-out to deep MLPs with any order. Performance of this method is evaluated on handwritten digits (MNIST), Fashion-MNIST, Free Spoken Digit Dataset (FSDD), and Street View House Numbers (SVHN) datasets and compared with the standard dropout and standout methods. Preliminary results show that the proposed approach can keep the classification performance competitive to the original network while eliminating optimization of unnecessary network parameters in each training cycle. This method can compress the inference model significantly while maintaining the classification performance.","PeriodicalId":221378,"journal":{"name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","volume":"292 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Ising Dropout with Node Grouping for Training and Compression of Deep Neural Networks\",\"authors\":\"H. Salehinejad, Zijian Wang, S. Valaee\",\"doi\":\"10.1109/GlobalSIP45357.2019.8969121\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Dropout is a popular regularization method to reduce over-fitting while training deep neural networks and compress the inference model. In this paper, we propose Ising dropout with node grouping, which represents a deep multilayer perceptron (MLP) neural network as a graph with fixed grouped nodes and uses the Ising energy to drop group of nodes. This method is an extension to our proposed Ising dropout method, which had the limit of solving the Ising energy model for MLPs with limited graph order. The proposed fixed grouping method enables applying drop-out to deep MLPs with any order. Performance of this method is evaluated on handwritten digits (MNIST), Fashion-MNIST, Free Spoken Digit Dataset (FSDD), and Street View House Numbers (SVHN) datasets and compared with the standard dropout and standout methods. Preliminary results show that the proposed approach can keep the classification performance competitive to the original network while eliminating optimization of unnecessary network parameters in each training cycle. This method can compress the inference model significantly while maintaining the classification performance.\",\"PeriodicalId\":221378,\"journal\":{\"name\":\"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)\",\"volume\":\"292 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GlobalSIP45357.2019.8969121\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GlobalSIP45357.2019.8969121","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

Dropout是一种常用的正则化方法,用于减少深度神经网络训练过程中的过拟合和压缩推理模型。本文提出了带节点分组的Ising dropout算法,该算法将深度多层感知器(MLP)神经网络表示为具有固定分组节点的图,并利用Ising能量来丢弃节点组。该方法是对我们提出的Ising dropout方法的扩展,该方法在求解具有有限图阶的mlp的Ising能量模型时存在局限性。提出的固定分组方法可以对任意阶次的深度mlp应用drop-out。在手写数字(MNIST)、时尚-MNIST、自由语音数字数据集(FSDD)和街景房屋号码(SVHN)数据集上对该方法的性能进行了评估,并与标准dropout和standout方法进行了比较。初步结果表明,该方法在消除每个训练周期中不必要的网络参数优化的同时,保持了与原始网络的分类性能竞争。该方法可以在保持分类性能的同时显著压缩推理模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Ising Dropout with Node Grouping for Training and Compression of Deep Neural Networks
Dropout is a popular regularization method to reduce over-fitting while training deep neural networks and compress the inference model. In this paper, we propose Ising dropout with node grouping, which represents a deep multilayer perceptron (MLP) neural network as a graph with fixed grouped nodes and uses the Ising energy to drop group of nodes. This method is an extension to our proposed Ising dropout method, which had the limit of solving the Ising energy model for MLPs with limited graph order. The proposed fixed grouping method enables applying drop-out to deep MLPs with any order. Performance of this method is evaluated on handwritten digits (MNIST), Fashion-MNIST, Free Spoken Digit Dataset (FSDD), and Street View House Numbers (SVHN) datasets and compared with the standard dropout and standout methods. Preliminary results show that the proposed approach can keep the classification performance competitive to the original network while eliminating optimization of unnecessary network parameters in each training cycle. This method can compress the inference model significantly while maintaining the classification performance.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信