Extrapolating from neural network models: a cautionary tale

A. Pastore, M. Carnini
{"title":"Extrapolating from neural network models: a cautionary tale","authors":"A. Pastore, M. Carnini","doi":"10.1088/1361-6471/abf08a","DOIUrl":null,"url":null,"abstract":"We present three different methods to estimate error bars on the predictions made using a neural network. All of them represent lower bounds for the extrapolation errors. For example, we did not include an analysis on robustness against small perturbations of the input data. \nAt first, we illustrate the methods through a simple toy model, then, we apply them to some realistic cases related to nuclear masses. By using theoretical data simulated either with a liquid-drop model or a Skyrme energy density functional, we benchmark the extrapolation performance of the neural network in regions of the Segre chart far away from the ones used for the training and validation. Finally, we discuss how error bars can help identifying when the extrapolation becomes too uncertain and thus unreliable","PeriodicalId":8463,"journal":{"name":"arXiv: Nuclear Theory","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv: Nuclear Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/1361-6471/abf08a","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

Abstract

We present three different methods to estimate error bars on the predictions made using a neural network. All of them represent lower bounds for the extrapolation errors. For example, we did not include an analysis on robustness against small perturbations of the input data. At first, we illustrate the methods through a simple toy model, then, we apply them to some realistic cases related to nuclear masses. By using theoretical data simulated either with a liquid-drop model or a Skyrme energy density functional, we benchmark the extrapolation performance of the neural network in regions of the Segre chart far away from the ones used for the training and validation. Finally, we discuss how error bars can help identifying when the extrapolation becomes too uncertain and thus unreliable
从神经网络模型推断:一个警世故事
我们提出了三种不同的方法来估计使用神经网络预测的误差条。它们都表示外推误差的下界。例如,我们没有包括对输入数据的小扰动的鲁棒性分析。首先,我们通过一个简单的玩具模型来说明这些方法,然后,我们将它们应用到一些与核质量有关的实际案例中。通过使用液滴模型或Skyrme能量密度函数模拟的理论数据,我们对Segre图中远离用于训练和验证的区域的神经网络的外推性能进行了基准测试。最后,我们讨论误差条如何帮助识别外推变得太不确定从而不可靠的情况
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
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