复值神经网络的定量逼近结果

IF 1.9 Q1 MATHEMATICS, APPLIED
A. Caragea, D. Lee, J. Maly, G. Pfander, F. Voigtlaender
{"title":"复值神经网络的定量逼近结果","authors":"A. Caragea, D. Lee, J. Maly, G. Pfander, F. Voigtlaender","doi":"10.1137/21m1429540","DOIUrl":null,"url":null,"abstract":"Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\\sigma(z) = \\mathrm{ReLU}(|z| - 1) \\, \\mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth.","PeriodicalId":74797,"journal":{"name":"SIAM journal on mathematics of data science","volume":"118 1","pages":"553-580"},"PeriodicalIF":1.9000,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Quantitative approximation results for complex-valued neural networks\",\"authors\":\"A. Caragea, D. Lee, J. Maly, G. Pfander, F. Voigtlaender\",\"doi\":\"10.1137/21m1429540\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\\\\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\\\\sigma(z) = \\\\mathrm{ReLU}(|z| - 1) \\\\, \\\\mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth.\",\"PeriodicalId\":74797,\"journal\":{\"name\":\"SIAM journal on mathematics of data science\",\"volume\":\"118 1\",\"pages\":\"553-580\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2021-02-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SIAM journal on mathematics of data science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1137/21m1429540\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICS, APPLIED\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIAM journal on mathematics of data science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1137/21m1429540","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}
引用次数: 4

摘要

直到最近,神经网络在机器学习中的应用几乎完全依赖于实值网络。然而,最近观察到,复杂值神经网络(cvnn)在输入自然是复杂值的应用中表现出优异的性能,例如MRI指纹识别。虽然到目前为止,实值网络的数学理论已经达到了一定的成熟程度,但对于复值网络来说,这还远远不够。本文通过给出复值神经网络在$\mathbb{C}^d$的紧子集上逼近$C^n$函数的显式定量误差界,分析了复值网络的可表达性。该复值神经网络使用的modReLU激活函数由$\sigma(z) = \ mathm {ReLU}(|z| - 1) \, \ mathm {sgn} (z)$给出,这是实践中最常用的复激活函数之一。我们表明,在权重适度增长的modReLU网络类中,导出的近似率是最优的(高达对数因子)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Quantitative approximation results for complex-valued neural networks
Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\sigma(z) = \mathrm{ReLU}(|z| - 1) \, \mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth.
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:481959085
Book学术官方微信