A tunable distance measure for coloured solid models
Artificial Intelligence
Emergence of symbolic behavior from brain like memory with dynamic attention
Neural Networks - Special issue on organisation of computation in brain-like systems
A general formulation of conceptual spaces as a meso level representation
Artificial Intelligence
Conceptual Spaces: The Geometry of Thought
Conceptual Spaces: The Geometry of Thought
A general formulation of conceptual spaces as a meso level representation
Artificial Intelligence
Modelling perceptual discrimination
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Hi-index | 0.00 |
Conceptual spaces have been proposed as a meso level representation, intermediate between symbolic and connectionist representations. We define a conceptual space to be a set of images or "voltage maps" on a compact sub plane, and equip it with pseudo-physiological notions of distance and betweenness. While our meso level representation is easily linked to higher and lower representations, we argue that its natural notion of geometry provides powerful additional tools for knowledge modeling and reasoning. As illustration, we offer an explanation of multi-dimensional experimental results which suggest distances follow different order Minkowski measures according to whether the dimensions are integral or separable.