Robust deep network learning of nonlinear regression tasks by parametric leaky exponential linear units (LELUs) and a diffusion metric

IF 6.8 1区 计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS
Enda D.V. Bigarella
{"title":"Robust deep network learning of nonlinear regression tasks by parametric leaky exponential linear units (LELUs) and a diffusion metric","authors":"Enda D.V. Bigarella","doi":"10.1016/j.ins.2025.122739","DOIUrl":null,"url":null,"abstract":"<div><div>This document proposes a parametric activation function (<em>ac.f</em>) aimed at improving multidimensional nonlinear data regression. It is an established knowledge that nonlinear <em>ac.f</em>s are required for learning nonlinear datasets. This work shows that smoothness and gradient properties of the <em>ac.f</em> further impact the performance of large neural networks in terms of overfitting and sensitivity to model parameters. Smooth but vanishing-gradient <em>ac.f</em>s such as ELU or SiLU (Swish) have limited performance, and non-smooth <em>ac.f</em>s such as RELU and Leaky-RELU further impart discontinuity in the trained model. Improved performance is demonstrated with a smooth “Leaky Exponential Linear Unit”, with non-zero gradient that can be trained. A novel diffusion-loss metric is also proposed to gauge the performance of the trained models in terms of overfitting.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"725 ","pages":"Article 122739"},"PeriodicalIF":6.8000,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Sciences","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0020025525008758","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

This document proposes a parametric activation function (ac.f) aimed at improving multidimensional nonlinear data regression. It is an established knowledge that nonlinear ac.fs are required for learning nonlinear datasets. This work shows that smoothness and gradient properties of the ac.f further impact the performance of large neural networks in terms of overfitting and sensitivity to model parameters. Smooth but vanishing-gradient ac.fs such as ELU or SiLU (Swish) have limited performance, and non-smooth ac.fs such as RELU and Leaky-RELU further impart discontinuity in the trained model. Improved performance is demonstrated with a smooth “Leaky Exponential Linear Unit”, with non-zero gradient that can be trained. A novel diffusion-loss metric is also proposed to gauge the performance of the trained models in terms of overfitting.
非线性回归任务的参数泄漏指数线性单元(LELUs)和扩散度量鲁棒深度网络学习
本文提出了一种改进多维非线性数据回归的参数激活函数(ac.f)。学习非线性数据集需要非线性ac.fs,这是一个公认的知识。这项工作表明,ac.f的平滑性和梯度特性进一步影响了大型神经网络在过拟合和对模型参数的敏感性方面的性能。平滑但梯度消失的ac.fs(如ELU或SiLU (Swish))性能有限,而非光滑的ac.fs(如RELU和Leaky-RELU)进一步赋予训练模型不连续性。改进的性能证明了光滑的“漏指数线性单元”,具有可以训练的非零梯度。本文还提出了一种新的扩散损耗度量来衡量训练模型的过拟合性能。
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
Information Sciences
Information Sciences 工程技术-计算机:信息系统
CiteScore
14.00
自引率
17.30%
发文量
1322
审稿时长
10.4 months
期刊介绍: Informatics and Computer Science Intelligent Systems Applications is an esteemed international journal that focuses on publishing original and creative research findings in the field of information sciences. We also feature a limited number of timely tutorial and surveying contributions. Our journal aims to cater to a diverse audience, including researchers, developers, managers, strategic planners, graduate students, and anyone interested in staying up-to-date with cutting-edge research in information science, knowledge engineering, and intelligent systems. While readers are expected to share a common interest in information science, they come from varying backgrounds such as engineering, mathematics, statistics, physics, computer science, cell biology, molecular biology, management science, cognitive science, neurobiology, behavioral sciences, and biochemistry.
×
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