论学习网络的权重动态

Nahal Sharafi, Christoph Martin, Sarah Hallerberg
{"title":"论学习网络的权重动态","authors":"Nahal Sharafi, Christoph Martin, Sarah Hallerberg","doi":"arxiv-2405.00743","DOIUrl":null,"url":null,"abstract":"Neural networks have become a widely adopted tool for tackling a variety of\nproblems in machine learning and artificial intelligence. In this contribution\nwe use the mathematical framework of local stability analysis to gain a deeper\nunderstanding of the learning dynamics of feed forward neural networks.\nTherefore, we derive equations for the tangent operator of the learning\ndynamics of three-layer networks learning regression tasks. The results are\nvalid for an arbitrary numbers of nodes and arbitrary choices of activation\nfunctions. Applying the results to a network learning a regression task, we\ninvestigate numerically, how stability indicators relate to the final\ntraining-loss. Although the specific results vary with different choices of\ninitial conditions and activation functions, we demonstrate that it is possible\nto predict the final training loss, by monitoring finite-time Lyapunov\nexponents or covariant Lyapunov vectors during the training process.","PeriodicalId":501167,"journal":{"name":"arXiv - PHYS - Chaotic Dynamics","volume":"60 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On the weight dynamics of learning networks\",\"authors\":\"Nahal Sharafi, Christoph Martin, Sarah Hallerberg\",\"doi\":\"arxiv-2405.00743\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neural networks have become a widely adopted tool for tackling a variety of\\nproblems in machine learning and artificial intelligence. In this contribution\\nwe use the mathematical framework of local stability analysis to gain a deeper\\nunderstanding of the learning dynamics of feed forward neural networks.\\nTherefore, we derive equations for the tangent operator of the learning\\ndynamics of three-layer networks learning regression tasks. The results are\\nvalid for an arbitrary numbers of nodes and arbitrary choices of activation\\nfunctions. Applying the results to a network learning a regression task, we\\ninvestigate numerically, how stability indicators relate to the final\\ntraining-loss. Although the specific results vary with different choices of\\ninitial conditions and activation functions, we demonstrate that it is possible\\nto predict the final training loss, by monitoring finite-time Lyapunov\\nexponents or covariant Lyapunov vectors during the training process.\",\"PeriodicalId\":501167,\"journal\":{\"name\":\"arXiv - PHYS - Chaotic Dynamics\",\"volume\":\"60 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Chaotic Dynamics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2405.00743\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Chaotic Dynamics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2405.00743","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

神经网络已成为解决机器学习和人工智能领域各种问题的广泛工具。因此,我们推导出了三层网络学习回归任务的学习动力学切线算子方程。这些结果对于任意节点数和任意激活函数的选择都是有效的。我们将结果应用于学习回归任务的网络,用数值方法研究了稳定性指标与最终训练损失之间的关系。虽然具体结果随初始条件和激活函数的不同选择而变化,但我们证明,通过在训练过程中监测有限时间 Lyapunovexponents 或协变 Lyapunov 向量,可以预测最终的训练损失。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
On the weight dynamics of learning networks
Neural networks have become a widely adopted tool for tackling a variety of problems in machine learning and artificial intelligence. In this contribution we use the mathematical framework of local stability analysis to gain a deeper understanding of the learning dynamics of feed forward neural networks. Therefore, we derive equations for the tangent operator of the learning dynamics of three-layer networks learning regression tasks. The results are valid for an arbitrary numbers of nodes and arbitrary choices of activation functions. Applying the results to a network learning a regression task, we investigate numerically, how stability indicators relate to the final training-loss. Although the specific results vary with different choices of initial conditions and activation functions, we demonstrate that it is possible to predict the final training loss, by monitoring finite-time Lyapunov exponents or covariant Lyapunov vectors during the training process.
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
期刊最新文献
Tunneling Time for Walking Droplets on an Oscillating Liquid Surface Rydberg excitons in cuprous oxide: A two-particle system with classical chaos Disruption of exo-asteroids around white dwarfs and the release of dust particles in debris rings in co-orbital motion Machine-aided guessing and gluing of unstable periodic orbits Nonequilibrium dynamics of coupled oscillators under the shear-velocity boundary condition
×
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