Multi-layer neural networks using generalized-mean neuron model

R. Yadav, N. Kumar, P. K. Kalra, J. John
{"title":"Multi-layer neural networks using generalized-mean neuron model","authors":"R. Yadav, N. Kumar, P. K. Kalra, J. John","doi":"10.1109/ISCIT.2004.1412457","DOIUrl":null,"url":null,"abstract":"Well structured higher order neurons have shown improved computational power and generalization ability. However, these models are difficult to train because of a combinatorial explosion of higher order terms as the number of inputs to the neuron increases. We present a neural network using a new neuron architecture called the generalized mean neuron (GMN) model. This neuron model consists of an aggregation function which is based on the generalized mean of all the inputs applied to it. The resulting neuron model has the same number of parameters with improved computational power as the existing multilayer perceptron (MLP) model. The capability of this model has been tested on the classification and time series prediction problems.","PeriodicalId":237047,"journal":{"name":"IEEE International Symposium on Communications and Information Technology, 2004. ISCIT 2004.","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE International Symposium on Communications and Information Technology, 2004. ISCIT 2004.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCIT.2004.1412457","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Well structured higher order neurons have shown improved computational power and generalization ability. However, these models are difficult to train because of a combinatorial explosion of higher order terms as the number of inputs to the neuron increases. We present a neural network using a new neuron architecture called the generalized mean neuron (GMN) model. This neuron model consists of an aggregation function which is based on the generalized mean of all the inputs applied to it. The resulting neuron model has the same number of parameters with improved computational power as the existing multilayer perceptron (MLP) model. The capability of this model has been tested on the classification and time series prediction problems.
采用广义平均神经元模型的多层神经网络
结构良好的高阶神经元具有较强的计算能力和泛化能力。然而,这些模型很难训练,因为随着神经元输入数量的增加,高阶项的组合爆炸。我们提出了一个神经网络使用一种新的神经元结构称为广义平均神经元(GMN)模型。该神经元模型由一个基于所有输入的广义均值的聚合函数组成。所得到的神经元模型具有与现有多层感知器(MLP)模型相同的参数数量,并且计算能力有所提高。在分类和时间序列预测问题上验证了该模型的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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