Generative learning for nonlinear dynamics

IF 44.8 1区 物理与天体物理 Q1 PHYSICS, APPLIED Nature Reviews Physics Pub Date : 2024-02-12 DOI:10.1038/s42254-024-00688-2
William Gilpin
{"title":"Generative learning for nonlinear dynamics","authors":"William Gilpin","doi":"10.1038/s42254-024-00688-2","DOIUrl":null,"url":null,"abstract":"Modern generative machine learning models are able to create realistic outputs far beyond their training data, such as photorealistic artwork, accurate protein structures or conversational text. These successes suggest that generative models learn to effectively parametrize and sample arbitrarily complex distributions. Beginning half a century ago, foundational works in nonlinear dynamics used tools from information theory for a similar purpose, namely, to infer properties of chaotic attractors from real-world time series. This Perspective article aims to connect these classical works to emerging themes in large-scale generative statistical learning. It focuses specifically on two classical problems: reconstructing dynamical manifolds given partial measurements, which parallels modern latent variable methods, and inferring minimal dynamical motifs underlying complicated data sets, which mirrors interpretability probes for trained models. Generative machine learning models seek to approximate and then sample the probability distribution of the data sets on which they are trained. This Perspective article connects these methods to historical studies of information processing and attractor geometry in nonlinear systems.","PeriodicalId":19024,"journal":{"name":"Nature Reviews Physics","volume":"6 3","pages":"194-206"},"PeriodicalIF":44.8000,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Reviews Physics","FirstCategoryId":"101","ListUrlMain":"https://www.nature.com/articles/s42254-024-00688-2","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, APPLIED","Score":null,"Total":0}
引用次数: 0

Abstract

Modern generative machine learning models are able to create realistic outputs far beyond their training data, such as photorealistic artwork, accurate protein structures or conversational text. These successes suggest that generative models learn to effectively parametrize and sample arbitrarily complex distributions. Beginning half a century ago, foundational works in nonlinear dynamics used tools from information theory for a similar purpose, namely, to infer properties of chaotic attractors from real-world time series. This Perspective article aims to connect these classical works to emerging themes in large-scale generative statistical learning. It focuses specifically on two classical problems: reconstructing dynamical manifolds given partial measurements, which parallels modern latent variable methods, and inferring minimal dynamical motifs underlying complicated data sets, which mirrors interpretability probes for trained models. Generative machine learning models seek to approximate and then sample the probability distribution of the data sets on which they are trained. This Perspective article connects these methods to historical studies of information processing and attractor geometry in nonlinear systems.

Abstract Image

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
非线性动力学的生成学习
现代生成式机器学习模型能够创建远远超出其训练数据的逼真输出,例如逼真的艺术作品、精确的蛋白质结构或会话文本。这些成功表明,生成模型能够有效地对任意复杂的分布进行参数化和采样。从半个世纪前开始,非线性动力学的奠基之作就利用信息论的工具实现了类似的目的,即从现实世界的时间序列中推断混沌吸引子的特性。本视角文章旨在将这些经典著作与大规模生成统计学习中的新兴主题联系起来。文章特别关注两个经典问题:给定部分测量值重建动态流形,这与现代潜变量方法相似;推断复杂数据集背后的最小动态图案,这反映了训练模型的可解释性探测。
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 去求助
来源期刊
CiteScore
47.80
自引率
0.50%
发文量
122
期刊介绍: Nature Reviews Physics is an online-only reviews journal, part of the Nature Reviews portfolio of journals. It publishes high-quality technical reference, review, and commentary articles in all areas of fundamental and applied physics. The journal offers a range of content types, including Reviews, Perspectives, Roadmaps, Technical Reviews, Expert Recommendations, Comments, Editorials, Research Highlights, Features, and News & Views, which cover significant advances in the field and topical issues. Nature Reviews Physics is published monthly from January 2019 and does not have external, academic editors. Instead, all editorial decisions are made by a dedicated team of full-time professional editors.
期刊最新文献
Science should inspire, but visions need nuance The AI revolution is always just out of reach The promise and peril of sociotechnical visions of the future Publisher Correction: Rydberg states of alkali atoms in atomic vapour as SI-traceable field probes and communications receivers Physics and the empirical gap of trustworthy AI
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1