Minds and Machines

, Volume 8, Issue 2, pp 161–179

Connectionism, Systematicity, and the Frame Problem

  • W.F.G. Haselager
  • J.F.H. van Rappard
Article

DOI: 10.1023/A:1008281603611

Cite this article as:
Haselager, W. & van Rappard, J. Minds and Machines (1998) 8: 161. doi:10.1023/A:1008281603611

Abstract

This paper investigates connectionism's potential to solve the frame problem. The frame problem arises in the context of modelling the human ability to see the relevant consequences of events in a situation. It has been claimed to be unsolvable for classical cognitive science, but easily manageable for connectionism. We will focus on a representational approach to the frame problem which advocates the use of intrinsic representations. We argue that although connectionism's distributed representations may look promising from this perspective, doubts can be raised about the potential of distributed representations to allow large amounts of complexly structured information to be adequately encoded and processed. It is questionable whether connectionist models that are claimed to effectively represent structured information can be scaled up to a realistic extent. We conclude that the frame problem provides a difficulty to connectionism that is no less serious than the obstacle it constitutes for classical cognitive science.

connectionismdistributed representationframe problemsystematicity

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • W.F.G. Haselager
    • 1
  • J.F.H. van Rappard
    • 1
  1. 1.Amsterdam / Vrije UniversiteitAmsterdamThe Netherlands