加权条件知识库有限多值语义下神经网络推理的ASP方法

IF 1.4 2区 数学 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING Theory and Practice of Logic Programming Pub Date : 2022-02-02 DOI:10.1017/S1471068422000163
Laura Giordano, Daniele Theseider Dupré
{"title":"加权条件知识库有限多值语义下神经网络推理的ASP方法","authors":"Laura Giordano, Daniele Theseider Dupré","doi":"10.1017/S1471068422000163","DOIUrl":null,"url":null,"abstract":"Abstract Weighted knowledge bases for description logics with typicality have been recently considered under a “concept-wise” multipreference semantics (in both the two-valued and fuzzy case), as the basis of a logical semantics of multilayer perceptrons (MLPs). In this paper we consider weighted conditional \n$\\mathcal{ALC}$\n knowledge bases with typicality in the finitely many-valued case, through three different semantic constructions. For the boolean fragment \n$\\mathcal{LC}$\n of \n$\\mathcal{ALC}$\n we exploit answer set programming and asprin for reasoning with the concept-wise multipreference entailment under a \n$\\varphi$\n -coherent semantics, suitable to characterize the stationary states of MLPs. As a proof of concept, we experiment the proposed approach for checking properties of trained MLPs.","PeriodicalId":49436,"journal":{"name":"Theory and Practice of Logic Programming","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2022-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":"{\"title\":\"An ASP Approach for Reasoning on Neural Networks under a Finitely Many-Valued Semantics for Weighted Conditional Knowledge Bases\",\"authors\":\"Laura Giordano, Daniele Theseider Dupré\",\"doi\":\"10.1017/S1471068422000163\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Weighted knowledge bases for description logics with typicality have been recently considered under a “concept-wise” multipreference semantics (in both the two-valued and fuzzy case), as the basis of a logical semantics of multilayer perceptrons (MLPs). In this paper we consider weighted conditional \\n$\\\\mathcal{ALC}$\\n knowledge bases with typicality in the finitely many-valued case, through three different semantic constructions. For the boolean fragment \\n$\\\\mathcal{LC}$\\n of \\n$\\\\mathcal{ALC}$\\n we exploit answer set programming and asprin for reasoning with the concept-wise multipreference entailment under a \\n$\\\\varphi$\\n -coherent semantics, suitable to characterize the stationary states of MLPs. As a proof of concept, we experiment the proposed approach for checking properties of trained MLPs.\",\"PeriodicalId\":49436,\"journal\":{\"name\":\"Theory and Practice of Logic Programming\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2022-02-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"16\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Theory and Practice of Logic Programming\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1017/S1471068422000163\",\"RegionNum\":2,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Theory and Practice of Logic Programming","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1017/S1471068422000163","RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 16

摘要

具有典型性的描述逻辑的抽象加权知识库最近被认为是在“概念方面”的多参考语义下(在二值和模糊的情况下),作为多层感知器(MLP)的逻辑语义的基础。在本文中,我们通过三种不同的语义结构,考虑在有限多值情况下具有典型性的加权条件$\mathcal{ALC}$知识库。对于$\mathcal{ALC}$的布尔片段$\mathical{LC}$,我们利用答案集编程和asprin,在$\varphi$相干语义下,利用概念多参考蕴涵进行推理,适用于表征MLP的平稳状态。作为概念验证,我们对所提出的检查训练MLP属性的方法进行了实验。
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
An ASP Approach for Reasoning on Neural Networks under a Finitely Many-Valued Semantics for Weighted Conditional Knowledge Bases
Abstract Weighted knowledge bases for description logics with typicality have been recently considered under a “concept-wise” multipreference semantics (in both the two-valued and fuzzy case), as the basis of a logical semantics of multilayer perceptrons (MLPs). In this paper we consider weighted conditional $\mathcal{ALC}$ knowledge bases with typicality in the finitely many-valued case, through three different semantic constructions. For the boolean fragment $\mathcal{LC}$ of $\mathcal{ALC}$ we exploit answer set programming and asprin for reasoning with the concept-wise multipreference entailment under a $\varphi$ -coherent semantics, suitable to characterize the stationary states of MLPs. As a proof of concept, we experiment the proposed approach for checking properties of trained MLPs.
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
Theory and Practice of Logic Programming
Theory and Practice of Logic Programming 工程技术-计算机:理论方法
CiteScore
4.50
自引率
21.40%
发文量
40
审稿时长
>12 weeks
期刊介绍: Theory and Practice of Logic Programming emphasises both the theory and practice of logic programming. Logic programming applies to all areas of artificial intelligence and computer science and is fundamental to them. Among the topics covered are AI applications that use logic programming, logic programming methodologies, specification, analysis and verification of systems, inductive logic programming, multi-relational data mining, natural language processing, knowledge representation, non-monotonic reasoning, semantic web reasoning, databases, implementations and architectures and constraint logic programming.
期刊最新文献
Metric Temporal Equilibrium Logic over Timed Traces Multi-Shot Answer Set Programming for Flexible Payroll Management Unit Testing in ASP Revisited: Language and Test-Driven Development Environment Evaluating Datalog Tools for Meta-reasoning over OWL 2 QL Model Explanation via Support Graphs
×
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