Inductive inference of approximations

Q4 Mathematics
James S. Royer
{"title":"Inductive inference of approximations","authors":"James S. Royer","doi":"10.1016/S0019-9958(86)80002-X","DOIUrl":null,"url":null,"abstract":"<div><p>In this paper we investigate inductive inference identification criteria which permit infinitely many errors in explanations, but which require that the “density” of these errors be no more than a certain, prespectified amount. We introduce three hierarchies of such criteria, each of which has the same order type as the real unit interval. These three hierarchies are progressively more strict in the way they measure density of errors of explanations. The strictest of the three turns out to have all of its members, save one, incomparable to the identification criterion which permits finitely many errors in explanations.</p></div>","PeriodicalId":38164,"journal":{"name":"信息与控制","volume":"70 2","pages":"Pages 156-178"},"PeriodicalIF":0.0000,"publicationDate":"1986-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0019-9958(86)80002-X","citationCount":"31","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"信息与控制","FirstCategoryId":"1093","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S001999588680002X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 31

Abstract

In this paper we investigate inductive inference identification criteria which permit infinitely many errors in explanations, but which require that the “density” of these errors be no more than a certain, prespectified amount. We introduce three hierarchies of such criteria, each of which has the same order type as the real unit interval. These three hierarchies are progressively more strict in the way they measure density of errors of explanations. The strictest of the three turns out to have all of its members, save one, incomparable to the identification criterion which permits finitely many errors in explanations.

近似的归纳推理
在本文中,我们研究了归纳推理识别准则,它允许在解释中有无限多的错误,但要求这些错误的“密度”不超过一个特定的、预先指定的量。我们引入了这样的准则的三个层次,每个层次都具有与实单位区间相同的阶型。这三个层次在衡量解释错误密度的方式上逐渐变得更加严格。三种标准中最严格的一种,除了一种以外,它的所有条件都与允许在解释中出现有限多错误的鉴定标准无法相比。
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
信息与控制
信息与控制 Mathematics-Control and Optimization
CiteScore
1.50
自引率
0.00%
发文量
4623
期刊介绍:
×
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