Towards structural systematicity in distributed, statically bound visual representations


  • Shimon Edelman,

    Corresponding author
    1. Department of Psychology, Cornell University, 232 Uris Hall, Ithaca, NY 14853-7601, USA
    Search for more papers by this author
  • Nathan Intrator

    1. Institute for Brain and Neural Systems, Brown University, P.O. Box 1843, Providence, RI 02912, USA
    Search for more papers by this author
    • On leave from the School Computer Science, Tel-Aviv University, Tel Aviv 69678, Israel.

Tel.: +1-607-255-6365; fax: +1-607-255-8433. E-mail address:


The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships. We argue that the main desiderata of a representational system—productivity and systematicity—can (indeed, for a number of reasons, should) be achieved without recourse to the classical, proposition-like compositionality. We show how this can be done, by describing a systematic and productive model of the representation of visual structure, which relies on static rather than dynamic binding and uses coarsely coded rather than atomic shape primitives.