The effect of amplitude modification in S-shaped activation functions on neural network regression

IF 0.7 4区 计算机科学 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Faizal Makhrus
{"title":"The effect of amplitude modification in S-shaped activation functions on neural network regression","authors":"Faizal Makhrus","doi":"10.14311/nnw.2023.33.015","DOIUrl":null,"url":null,"abstract":"Time series forecasting using multilayer feed-forward neural networks (FNN) is potential to give high accuracy. Several factors influence the accuracy. One of them is the choice of activation functions (AFs). There are several AFs commonly used in FNN with their specific characteristics, such as bounded type AFs. They include sigmoid, softsign, arctan, and tanh. This paper investigates the effect of the amplitude in the bounded AFs on the FNNs’ accuracy. The theoretical investigations use simplified FNN models: linear equation and linear combination. The results show that the higher amplitudes give higher accuracy than typical amplitudes in softsign, arctan, and tanh AFs. However, in sigmoid AF, the amplitude changes do not influence the accuracy. These theoretical results are supported by experiments using the FNN model for time series prediction of 10 foreign exchanges from different continents compared to the US dollar. Based on the experiments, the optimum amplitude of the AFs should be high, that is greater or equal to 100 times of the maximum input values to the FNN, and the accuracy gains up to 3–10 times.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":"0"},"PeriodicalIF":0.7000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Network World","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14311/nnw.2023.33.015","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Time series forecasting using multilayer feed-forward neural networks (FNN) is potential to give high accuracy. Several factors influence the accuracy. One of them is the choice of activation functions (AFs). There are several AFs commonly used in FNN with their specific characteristics, such as bounded type AFs. They include sigmoid, softsign, arctan, and tanh. This paper investigates the effect of the amplitude in the bounded AFs on the FNNs’ accuracy. The theoretical investigations use simplified FNN models: linear equation and linear combination. The results show that the higher amplitudes give higher accuracy than typical amplitudes in softsign, arctan, and tanh AFs. However, in sigmoid AF, the amplitude changes do not influence the accuracy. These theoretical results are supported by experiments using the FNN model for time series prediction of 10 foreign exchanges from different continents compared to the US dollar. Based on the experiments, the optimum amplitude of the AFs should be high, that is greater or equal to 100 times of the maximum input values to the FNN, and the accuracy gains up to 3–10 times.
s形激活函数振幅修正对神经网络回归的影响
利用多层前馈神经网络(FNN)进行时间序列预测具有较高的精度。有几个因素影响精度。其中之一是激活函数(AFs)的选择。在FNN中常用的AFs有其特定的特性,如有界型AFs。它们包括s型、软型、arctan和tanh。本文研究了有界AFs的振幅对fnn精度的影响。理论研究采用简化的FNN模型:线性方程和线性组合。结果表明,在软信号、arctan和tanh af中,较高的振幅比典型振幅具有更高的精度。然而,在s形自动对焦中,振幅变化不影响精度。这些理论结果得到了实验的支持,使用FNN模型对来自不同大陆的10种外汇进行时间序列预测,并与美元进行比较。实验结果表明,AFs的最佳幅值应较大,即大于或等于FNN最大输入值的100倍,精度可提高3 ~ 10倍。
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
Neural Network World
Neural Network World 工程技术-计算机:人工智能
CiteScore
1.80
自引率
0.00%
发文量
0
审稿时长
12 months
期刊介绍: Neural Network World is a bimonthly journal providing the latest developments in the field of informatics with attention mainly devoted to the problems of: brain science, theory and applications of neural networks (both artificial and natural), fuzzy-neural systems, methods and applications of evolutionary algorithms, methods of parallel and mass-parallel computing, problems of soft-computing, methods of artificial intelligence.
×
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:481959085
Book学术官方微信