A general formulation of conceptual spaces as a meso level representation

被引:46
作者
Aisbett, J [1 ]
Gibbon, G [1 ]
机构
[1] Univ Newcastle, Sch Informat Technol, Callaghan, NSW, Australia
关键词
concept representation; cognitive processing; feature spaces; dynamical systems; knowledge representation; conceptual spaces; representational levels; categorisation; prototypes; conceptual distances;
D O I
10.1016/S0004-3702(01)00144-8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Representing cognitive processes remains one of the great research challenges. Many important application areas, such as clinical diagnosis, operate in an environment of relative magnitudes, counts, shapes, colours, etc. which are not well captured by current representational approaches. This paper presents conceptual spaces as a meso level representation for cognitive systems, between the high level symbolic representations and the subconceptual connectionist representations which have dominated Al. Conceptual spaces emphasize orders and measures and therefore naturally represent counts, magnitudes, and volumes. Taking Gardenfors' decade-long investigation of conceptual spaces [Gardenfors, Conceptual Spaces: The Geometry of Thought, MIT Press, 2000] as start point, the paper presents a formal foundation for conceptual spaces, shows how they are theoretically and practically linked to higher and lower representational levels, and develops dynamics which allow the orbits of states in the space to solve appropriate meso level reasoning tasks. Interpretations of conceptual spaces are given to illustrate the formal definitions and show the flexibility of the representation. (C) 2001 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:189 / 232
页数:44
相关论文
共 43 条
[1]   A TUNABLE DISTANCE MEASURE FOR COLORED SOLID MODELS [J].
AISBETT, J ;
GIBBON, G .
ARTIFICIAL INTELLIGENCE, 1994, 65 (01) :143-164
[2]  
AISBETT J, 2001, P 6 INT WORK C ART N
[3]  
BARSALOU L, 1997, BEHAV BRAIN SCI, V22, P577
[4]  
BORSUK K, 1960, FDN GEOMETRY
[5]   ART-3 - HIERARCHICAL SEARCH USING CHEMICAL TRANSMITTERS IN SELF-ORGANIZING PATTERN-RECOGNITION ARCHITECTURES [J].
CARPENTER, GA ;
GROSSBERG, S .
NEURAL NETWORKS, 1990, 3 (02) :129-152
[6]   ARTMAP - SUPERVISED REAL-TIME LEARNING AND CLASSIFICATION OF NONSTATIONARY DATA BY A SELF-ORGANIZING NEURAL NETWORK [J].
CARPENTER, GA ;
GROSSBERG, S ;
REYNOLDS, JH .
NEURAL NETWORKS, 1991, 4 (05) :565-588
[7]   A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].
CARPENTER, GA ;
GROSSBERG, S .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115
[8]   Understanding dynamic scenes [J].
Chella, A ;
Frixione, M ;
Gaglio, S .
ARTIFICIAL INTELLIGENCE, 2000, 123 (1-2) :89-132
[9]  
Clark A., 1993, Sensory Qualities
[10]   VARIETIES OF NUMERICAL ABILITIES [J].
DEHAENE, S .
COGNITION, 1992, 44 (1-2) :1-42