Search
2013 Volume 28
Article Contents
RESEARCH ARTICLE   Open Access    

Visuo: A model of visuospatial instantiation of quantitative magnitudes

More Information
  • 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 predicts quantitative knowledge to new concepts.
  • 加载中
  • Bird S. G., Loper E.2004. NLTK: The Natural Language Toolkit. In Proceedings of the 42nd Meeting of the Association for Computational Linguistics (Demonstration Track), Barcelona, Spain, 214–217.

    Google Scholar

    Daugman J. P.1985. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A2, 1160–1169.

    Google Scholar

    Dehaene S., Izard V., Spelke E., Pica P.2008. Log or linear? Distinct intuitions of the number scale in Western and Amazonian Indigene cultures. Science320(5880), 1217–1220.

    Google Scholar

    Dubois D., Prade H.1987. Fuzzy numbers: an overview. In Analysis of Fuzzy Information Vol. I: Mathematics and Logic, Bezdek, J. C. (ed.). CRC Press.

    Google Scholar

    Fellbaum C. (ed.) 1998. WordNet: An Electronic Lexical Database. MIT Press.

    Google Scholar

    Hampton J. A.2007. Typicality, graded membership, and vagueness. Cognitive Science31(3), 355–384.

    Google Scholar

    Hubel D. A., Wiesel T. N.1965. Receptive fields and functional architecture in two non-striate visual areas (18 and 19) of the cat. Journal of Neurophysiology28, 229–289.

    Google Scholar

    Jones J. P., Palmer L. A.1987. An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology58, 1233–1258.

    Google Scholar

    Kreiman G., Koch C., Fried I.2000a. Category-specific visual responses of single neurons in the human medial temporal lobe. Nature Neuroscience3, 946–953.

    Google Scholar

    Kreiman G., Koch C., Fried I.2000b. Imagery neurons in the human brain. Nature408, 357–361.

    Google Scholar

    Negnevitsky M.2005. Artificial Intelligence: A Guide to Intelligent Systems, 2nd edition. Addison-Wesley.

    Google Scholar

    Perret D. I., Hietanen J. K., Oram M. W., Benson P. J.1992. Organization and function of cells responsive to faces in the temporal cortex. Philosophical Transactions of the Royal Society of London Series B.335, 1273, 23–30.

    Google Scholar

    Pollen D. A., Ronner S. F.1981. Phase relationships between adjacent simple cells in the visual cortex. Science212, 1409–1411.

    Google Scholar

    Rosch E. H.1973. Natural categories. Cognitive Psychology4, 328–350.

    Google Scholar

    Tanaka K.1993. Neuronal mechanisms of object recognition. Science262, 684–688.

    Google Scholar

    Tulving E.1984. Precis of elements of episodic memory. Behavioral and Brain Sciences7, 223–268.

    Google Scholar

    von Ahn L., Liu R., Blum M.2006. Peekaboom: A Game for Locating Objects In Images. Computer–Human Interaction Conference. Montréal, Québec, Canada, 55–64.

    Google Scholar

    Wu Z., Palmer M.1994. Verb semantics and lexical selection. In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, Las Cruces, New Mexico, 133–138.

    Google Scholar

    Zadeh L. A.1965. Fuzzy sets. Information and Control8(3), 338–353.

    Google Scholar

  • Cite this article

    Jonathan Gagné, Jim Davies. 2013. Visuo: A model of visuospatial instantiation of quantitative magnitudes. The Knowledge Engineering Review 28(3)347−366, doi: 10.1017/S0269888913000283
    Jonathan Gagné, Jim Davies. 2013. Visuo: A model of visuospatial instantiation of quantitative magnitudes. The Knowledge Engineering Review 28(3)347−366, doi: 10.1017/S0269888913000283

Article Metrics

Article views(23) PDF downloads(37)

Other Articles By Authors

RESEARCH ARTICLE   Open Access    

Visuo: A model of visuospatial instantiation of quantitative magnitudes

The Knowledge Engineering Review  28 2013, 28(3): 347−366  |  Cite this article

Abstract: 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 predicts quantitative knowledge to new concepts.

    • For low numbers, it only approximates the logarithmic scale; 0 is not in the logarithmic scale.

    • The latter should not be confused with float notation used in computer science.

    • This depends on the scale used. On a logarithmic scale, a concept would have a flatter distribution only if log(source_distribution) < log(target_distribution).

    • Copyright © Cambridge University Press 2013 2013Cambridge University Press
References (19)
  • About this article
    Cite this article
    Jonathan Gagné, Jim Davies. 2013. Visuo: A model of visuospatial instantiation of quantitative magnitudes. The Knowledge Engineering Review 28(3)347−366, doi: 10.1017/S0269888913000283
    Jonathan Gagné, Jim Davies. 2013. Visuo: A model of visuospatial instantiation of quantitative magnitudes. The Knowledge Engineering Review 28(3)347−366, doi: 10.1017/S0269888913000283
  • Catalog

      /

      DownLoad:  Full-Size Img  PowerPoint
      Return
      Return