Skip to main content
SpringerLink
Log in

Grounding symbols into perceptions

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

This paper deals with symbol formation, from a cognitive point of view, through a connectionist model.

To give an idea of our aim, let us consider the metaphor of learning to play tennis. Two knowledge forms are involved:

  • - implicit knowledge, e.g. sensori-motor associations; this knowledge is subsymbolic

  • - explicit knowledge, e.g. a teacher giving verbal advice, which makes use of symbols.

Learned knowledge consists of a combination of subsymbolic and symbolic items. More than a juxtaposition, this combination involves grounding symbols into a subsymbolic substratum. This leads us to connectionist modelling which is considered as the common framework for both kinds of knowledge.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Barto, A. G. & Sutton, R. S. (1981). Landmark Learning: An Illustration of Associative Search. Biological Cybernetics 42: 1–8.

    Google Scholar 

  • Grumbach, A. (1994) Cognition artificielle, Du réflexe ... à la réflexion. Addison Wesley: Paris.

    Google Scholar 

  • Hendler, J. (1991). Developing Hybrid Symbolic/Connectionist Models. In Barnden, J. (ed.) Advances in Connectionist and Neural Computation Theory, Ch. 7, pp. 165–179.

  • Hofstadter, D. (1980). Gödel, Escher, Bach. Vintage Books, pp. 349.

  • Nenov, V. I. & Dyer, M. G. (1988). DETE System: Connectionists/Symbolic Model of Visual Verbal Association. Proceedings of the International Conference on Neural Networks, Vol. II, pp. 17–24.

    Google Scholar 

  • Ogden, C. K. & Richards, I. A. (1923). The Meaning of Meaning. Routledge and Kegan Paul: London.

    Google Scholar 

  • Piaget, J. (1978). La formation du symbole chez l'enfant. Delachaux et Niestlé: Neuchâtel-Paris.

    Google Scholar 

  • Regier, T. (1992). The Acquisition of Lexical Semantics for Spatial Terms: A Connectionist Model of Perceptual Categorization. Computer Science Division, EECS Department, University of California Berkeley dissertation, TR-92-062.

  • Shastri, L. & Feldman, J. A. (1984). Semantic Networks and Neural Nets. University of Rochester, TR 131.

  • Shavlik, J. W. (1992). A Framework for Combining Symbolic and Neural Learning. Computer Science Dept., University of Wisconsin-Maddison, TR 1123.

  • Sorouchyari, E. (1989). Mobile Robot Navigation: A Neural Network Approach. Proceedings of Journées d'Electronique, Ecole Polytechnique Fédérale de Lausanne, pp. 159–175.

  • Ritter, H., Martinez, T. & Schulten, K. (1989). Topology Conserving Maps for Learning Visuo-Motor Coordination. Neural Networks 2: 159–168.

    Google Scholar 

  • Towell, G. G. & Shavlik, J. W. (1994). Knowledge-Based Artificial Neural Network. Artificial Intelligence 70, Nos. 1–2, 119–165.

    Google Scholar 

  • Werner, H. & Kaplan, B. (1963). Symbol Formation. Wiley: New York.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. E.N.S.T., 46 rue Barrault, 75634, Paris Cedex 13, France

    Alain Grumbach

Authors
  1. Alain Grumbach
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This research was supported by French CNRS “Réseau Cogni-Centre” and “GDR 957”. This paper is published by courtesy of HERMES editor who published a previous French version in “Technique et Science Informatiques” Vol. 12, no. 3, 1993, pp. 347–369.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Grumbach, A. Grounding symbols into perceptions. Artif Intell Rev 10, 131–146 (1996). https://doi.org/10.1007/BF00159219

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00159219

Key words

Search

Navigation