用于系统识别的深度网络:调查

IF 4.8 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS
Gianluigi Pillonetto , Aleksandr Aravkin , Daniel Gedon , Lennart Ljung , Antônio H. Ribeiro , Thomas B. Schön
{"title":"用于系统识别的深度网络:调查","authors":"Gianluigi Pillonetto ,&nbsp;Aleksandr Aravkin ,&nbsp;Daniel Gedon ,&nbsp;Lennart Ljung ,&nbsp;Antônio H. Ribeiro ,&nbsp;Thomas B. Schön","doi":"10.1016/j.automatica.2024.111907","DOIUrl":null,"url":null,"abstract":"<div><p>Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input–output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning-based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that have emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting and double-descent. Finally, we highlight numerical, computational and software aspects in the area with the help of applied examples.</p></div>","PeriodicalId":55413,"journal":{"name":"Automatica","volume":"171 ","pages":"Article 111907"},"PeriodicalIF":4.8000,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0005109824004011/pdfft?md5=369128fac8aa3dbd37df831300f34a92&pid=1-s2.0-S0005109824004011-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Deep networks for system identification: A survey\",\"authors\":\"Gianluigi Pillonetto ,&nbsp;Aleksandr Aravkin ,&nbsp;Daniel Gedon ,&nbsp;Lennart Ljung ,&nbsp;Antônio H. Ribeiro ,&nbsp;Thomas B. Schön\",\"doi\":\"10.1016/j.automatica.2024.111907\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input–output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning-based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that have emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting and double-descent. Finally, we highlight numerical, computational and software aspects in the area with the help of applied examples.</p></div>\",\"PeriodicalId\":55413,\"journal\":{\"name\":\"Automatica\",\"volume\":\"171 \",\"pages\":\"Article 111907\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-09-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0005109824004011/pdfft?md5=369128fac8aa3dbd37df831300f34a92&pid=1-s2.0-S0005109824004011-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Automatica\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0005109824004011\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automatica","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0005109824004011","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

深度学习是当前备受关注的话题。海量数据收集和强大软件资源的可用性为许多应用领域带来了令人印象深刻的成果,这些成果揭示了观察结果的基本但隐藏的属性。系统识别从输入输出数据中学习动态系统的数学描述,因此可以从深度神经网络的进步中获益,从而丰富可供选择的模型范围。为此,我们从系统识别的角度对深度学习进行了研究。我们涵盖了广泛的主题,使研究人员能够理解这些方法,对使用这些方法的益处和挑战提供了严谨的实践和理论见解。识别模型的主要目的是根据以前的观测结果预测新数据。这可以通过不同的基于深度学习的建模技术来实现,我们将讨论文献中通常采用的架构,如前馈、卷积和递归网络。它们的参数必须根据过去的数据进行估计,以优化预测性能。为此,我们讨论了一组特定的一阶优化工具,这些工具已成为高效工具。然后,调查将基于核的方法与已被广泛研究的领域联系起来。它们通过正则化项控制数据拟合,惩罚不符合先验假设的模型。我们说明了如何将它们应用于深度架构,从而获得基于内核的深度方法。深度学习的成功也带来了令人惊讶的经验观察,比如具有许多参数的模型的反直觉行为。我们讨论了过参数化模型的作用,包括它们与核的联系,以及影响泛化的隐式正则化机制,特别是良性过拟合和双后裔的有趣现象。最后,我们通过应用实例强调了该领域的数值、计算和软件方面。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep networks for system identification: A survey

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input–output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning-based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that have emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting and double-descent. Finally, we highlight numerical, computational and software aspects in the area with the help of applied examples.

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
Automatica
Automatica 工程技术-工程:电子与电气
CiteScore
10.70
自引率
7.80%
发文量
617
审稿时长
5 months
期刊介绍: Automatica is a leading archival publication in the field of systems and control. The field encompasses today a broad set of areas and topics, and is thriving not only within itself but also in terms of its impact on other fields, such as communications, computers, biology, energy and economics. Since its inception in 1963, Automatica has kept abreast with the evolution of the field over the years, and has emerged as a leading publication driving the trends in the field. After being founded in 1963, Automatica became a journal of the International Federation of Automatic Control (IFAC) in 1969. It features a characteristic blend of theoretical and applied papers of archival, lasting value, reporting cutting edge research results by authors across the globe. It features articles in distinct categories, including regular, brief and survey papers, technical communiqués, correspondence items, as well as reviews on published books of interest to the readership. It occasionally publishes special issues on emerging new topics or established mature topics of interest to a broad audience. Automatica solicits original high-quality contributions in all the categories listed above, and in all areas of systems and control interpreted in a broad sense and evolving constantly. They may be submitted directly to a subject editor or to the Editor-in-Chief if not sure about the subject area. Editorial procedures in place assure careful, fair, and prompt handling of all submitted articles. Accepted papers appear in the journal in the shortest time feasible given production time constraints.
×
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