Advertisement

An associative link from geometric to symbolic representations in artificial vision

  • E. Ardizzone
  • F. Callari
  • A. Chella
  • M. Frixione
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 549)

Abstract

Recent approaches to modelling the reference of internal symbolic representations of intelligent systems suggest to consider a computational level of a subsymbolic kind. In this paper the integration between symbolic and subsymbolic processing is approached in the framework of the research work currently carried on by the authors in the field of artificial vision. An associative mapping mechanism is defined in order to relate the constructs of the symbolic representation to a geometric model of the observed scene.

The implementation of the mapping mechanism by means of a neural network architecture is described taking into account both the backpropagation architecture and the Boltzmann machine architecture. Promising experimental results are discussed.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Ardizzone, E., Gaglio, S., Sorbello, F. (1989). Geometric and Conceptual Knowledge Representation within a Generative Model of Visual Perception, Journal of Intelligent and Robotic Systems, 2, 381–409.Google Scholar
  2. [2]
    Ardizzone, E., Chella, A., Frixione, M., Gaglio, S. (1990). Integrating Subsymbolic and Symbolic Processing in Artificial Vision, submitted to Journal of Intelligent Systems.Google Scholar
  3. [3]
    Brachman, R.J., Schmolze, J. (1985). An overview of the KL-ONE knowledge representation system, Cognitive Science, 9, 171–216.Google Scholar
  4. [4]
    Frixione, M., Spinelli, G., Gaglio, S. (1989). Symbols and subsymbols for representing knowledge: a catalogue raisonne', Proc. of the Tenth IJCAI, 3–7, Detroit, USA.Google Scholar
  5. [5]
    Gaglio, S., Spinelli, G., Tagliasco, V. (1984). Visual Perception: an Outline of a Generative Theory of Information Flow Organization, Theoretical Linguistics, 11, 21–43.Google Scholar
  6. [6]
    Galland, C.C., Hinton, G.E. (1989). Deterministic Boltzmann Learning in Networks with Asymmetric Connectivity, Techn. Rep. CRG-TR-89-6, University of Toronto, Canada.Google Scholar
  7. [7]
    Goddard, N.H., Lynne, K.J., Mintz, T., Bukys, L. (1989). Rochester Connectionist Simulator, Techn.Rep. 233, University of Rochester, New York, USA.Google Scholar
  8. [8]
    Pentland, A.P. (1986). Perceptual Organization and the Representation of Natural Form, Artificial Intelligence, 28, 293–331.Google Scholar
  9. [9]
    Smolensky, P. (1988). On the hypotheses underyingconnectionism, Behavioral and Brain Sciences, 11, 1.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • E. Ardizzone
    • 1
  • F. Callari
    • 1
  • A. Chella
    • 1
    • 2
  • M. Frixione
    • 3
    • 4
  1. 1.DIE-Dipartimento di Ingegneria ElettricaUniversity of PalermoPalermoItaly
  2. 2.CRES-Centro per la Ricerca Elettronica in SiciliaMonreale (Palermo)Italy
  3. 3.Dipartimento di FilosofiaUniversity of GenovaGenovaItaly
  4. 4.DIST-Dipartimento di Informatica, Sistemistica e TelematicaUniversity of GenovaGenovaItaly

Personalised recommendations