Reasoning and learning in the setting of possibility theory - Overview and perspectives

被引:4
作者
Dubois, Didier
Prade, Henri
机构
关键词
Possibility theory; Possibilistic logic; Uncertainty; Knowledge representation; Reasoning; Machine learning; CONSTRAINT SATISFACTION PROBLEMS; BELIEF FUNCTIONS; FUZZY-SETS; PROBABILITY-DISTRIBUTIONS; SUGENO INTEGRALS; INFORMATION; LOGIC; REPRESENTATIONS; INDEPENDENCE; UNCERTAINTY;
D O I
10.1016/j.ijar.2023.109028
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Possibility theory stands halfway between logical and probabilistic representation frameworks. Possibility theory, as a setting for handling epistemic uncertainty, may have a qualitative or a quantitative flavor depending on the way conditioning is defined. In particular, qualitative possibility theory is totally compatible with classical logic, while quantitative possibility theory is related to statistics. This feature suggests the possibility theory setting as an interesting candidate for interfacing reasoning and learning. The potential of the possibilistic representation framework for reasoning, explanation and learning tasks is particularly highlighted. (c) 2023 Published by Elsevier Inc.
引用
收藏
页数:19
相关论文
共 166 条
[1]   Connecting Dempster-Shafer belief functions with likelihood-based inference [J].
Aickin, M .
SYNTHESE, 2000, 123 (03) :347-364
[2]  
Ait-Yakoub Z., 2016, P 5 INT WORKSHOP WHA, P79
[3]   Asymmetric Composition of Possibilistic Operators in Formal Concept Analysis: Application to the Extraction of Attribute Implications from Incomplete Contexts [J].
Ait-Yakoub, Zina ;
Djouadi, Yassine ;
Dubois, Didier ;
Prade, Henri .
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2017, 32 (12) :1285-1311
[4]  
Alsinet T., 2000, P 16 C UNC AI UAI 00, P1
[5]  
Amor NB, 2003, SOFT COMPUT, V8, P150, DOI [10.1007/s00500-002-0255-x, 10.1007/S00500-002-0255-X]
[6]  
ANGLUIN D, 1992, MACH LEARN, V9, P147, DOI 10.1007/BF00992675
[7]  
Angluin D., 1988, Machine Learning, V2, P319, DOI 10.1023/A:1022821128753
[8]  
[Anonymous], 1961, Shackle
[9]  
[Anonymous], 2001, P 17 C UNC ART INT U
[10]  
Ayachi R., 2012, CCIS, V299, P470