[ home | resume | contact | science | art | personal | email ]

Gagné, J. & Davies, J. (2009). Analogical estimation of quantitative magnitudes. New Frontiers of Analogy Research: Proceedings of Analogy 09, 155--164, Sofia, Bulgaria.

Cite this for: Publisher: http://www.nbu.bg/cogs/analogy09/

BibTex Entry:

@InProceedings{GagneDavies2009,
  author = 	 {Davies, Jim and Gagn\'{e}, Jonathan},
  title = 	 {Analogical estimation of quantitative magnitudes},
  booktitle = 	 {New Frontiers of Analogy Research: Proceedings of Analogy 09},
  pages = 	 {155-164},
  year = 	 {2009},
  editor = 	 {B. Kokinov},
  address = 	 {Sofia, Bulgaria}
}

Choose download format: [ PDF ]

From the Visual Analogy research theme.

Abstract

Visuo is an implemented Python program that models visual reasoning. It takes as input a description of a scene in words (e.g., “small dog on a sunny street”) and produces estimates of the quantitative magnitudes of the qualitative input (e.g., the size of the dog and the brightness of the street). We claim that reasoners transfer quantitative knowledge to new concepts from distributions of familiar concepts in memory. We also claim that visuospatial magnitudes should be stored as distributions over fuzzy sets. We show that Visuo successfully adapts knowledge to new concepts.

Back to Jim Davies's list of publications.


JimDavies ( jim@jimdavies.org )