Minds and Machines

, Volume 8, Issue 2, pp 161–179 | Cite as

Connectionism, Systematicity, and the Frame Problem

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


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.

connectionism distributed representation frame problem systematicity 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bechtel, W., and Abrahamsen, A. (1991), Connectionism and the Mind, Oxford: Blackwell.Google Scholar
  2. Butler, K. (1993), Connectionism, Classical Cognitivism and the Relation between Cognitive and implementational Levels of Analysis, Philosophical Psychology, 6(3), pp 321–333.Google Scholar
  3. Chalmers, D.J. (1990), "syntactic Transformations on Distributed Representation, Connection Science, 2(1 & 2), 53–62.Google Scholar
  4. Chalmers, D.J. (1993), ‘Connectionism and Compositionality: why Fodor and Pylyshyn were Wrong, Philosophical Psychology, 6(3), pp.305–319.Google Scholar
  5. Christiansen, M.H., and Chater, N. (1994), Generalization and Connectionist Language Learning, Mind & Language, 9(3), pp.273–287.Google Scholar
  6. Churchland, P.M. (1989), A Neurocomputational Perspective: The Nature of Mind and the Structure of Science, Cambridge: MIT Press.Google Scholar
  7. Churchland, P.M. (1995), The Engine of Reason, the Seat of the Soul: A Philosophical Journey into the Brain, Cambridge: MIT Press.Google Scholar
  8. Churchland, P.S., and Sejnowski, T.J. (1992), The Computational Brain, Cambridge: MIT Press.Google Scholar
  9. Clark, A. (1992), ‘The presence of a Symbol’, Connection Science, 4,3 and 4, pp. 193–205.Google Scholar
  10. Clark, A., and Thornton, C. (in press), ‘Trading Spaces: Computation, Representation and the Limits of Uninformed Learning’, Behavioral and Brain Sciences.Google Scholar
  11. Dennett, D.C. (1991), ‘Mother Nature Versus the Walking Encyclopedia: A Western Drama’, in W. Ramsey, S. Stich and D. Rumelhart (eds.), Philosophy and Connectionist theory, Hillsdale: Erlbaum pp 21–30.Google Scholar
  12. Derthick, M. (1990), ‘Mundane Reasoning by Settling on a Plausible Model’. Artificial Intelligence, 46 pp., 107–157.Google Scholar
  13. Dreyfus, H.L. (1965), Alchemy and Artificial Intelligence, The RAND corporation paper P-3244.Google Scholar
  14. Dreyfus, H.L., and Dreyfus, S.E. (1986), Mind Over Machine: The Power of Human Intuition and Expertise in the Era of the Computer, New York: The Free Press.Google Scholar
  15. Dreyfus, H.L., and Dreyfus, S.E. (1987), How to Stop Worrying about the Frame Problem even though it is Computationally Insoluable, in Z. W. Pylyshyn (Ed.), The Robot's Dilemma: the Frame Problem in Artificial Intelligence Norwood: Ablex (pp. 95–112)Google Scholar
  16. Elman, J.L. (1991), ‘Distributed Representations, Simple Recurrent Networks, and Grammatical Structure, Machine Learning’, 7, pp. 195–225.Google Scholar
  17. Elman, J.L. (1993), ‘Learning and Development in Neural Networks: the Importance of Starting Small’, Cognition, 48, pp.71–99.Google Scholar
  18. Feldman, J.A. (1989), ‘Neural Representation of Conceptual Knowledge’, in L. Nadel, L.A. Cooper, P. Culicover, and R. M. Harnish (eds.), Neural Connections, Mental Computation Cambridge: MIT Press (pp. 68–103).Google Scholar
  19. Fetzer, J.H. (1991), ‘The Frame Problem: Artificial Intelligence Meets David Hume’, in K.M. Ford and P.J. Hayes (eds.), Reasoning Agents in a Dynamical World: the Frame Problem London: JAI Press (pp. 55–69).Google Scholar
  20. Fodor, J.A. (1975), The language of thought, Cambridge: Harvard University Press.Google Scholar
  21. Fodor, J.A. (1987), Psychosemantics: the Problem of Meaning in the Philosophy of Mind, Cambridge: MIT Press.Google Scholar
  22. Fodor, J.A., and McLaughlin, B. (1990), ‘Connectionism and the Problem of Systematicity: Why Smolensky's Solution does not work’, Cognition, 35, 183–204.Google Scholar
  23. Fodor, J.A., and Pylyshyn, Z. W. (1988), ‘Connectionism and cognitive architecture’, Cognition, 28, 3–71.Google Scholar
  24. Hadley, R.F. (1994a), ‘Systematicity in Connectionist Language Learning’, Mind and Language, 9(3), pp.247–272.Google Scholar
  25. Hadley, R.F. (1994b), ‘Systematicity revisited: reply to Christiansen, Chater, Niklasson and van Gelder’, Mind and Language, 9(4), pp.431–444.Google Scholar
  26. Hadley, R.F. (1995), ‘The ‘Explicit-implicit’ Distinction’, Minds and Machines, 5, pp.219–242.Google Scholar
  27. Haselager, W.F.G. (1997), Cognitive Science and Folk Psychology: The Right Frame of Mind, London: Sage Publications.Google Scholar
  28. Haugeland, J. (1987), ‘An overview of the Frame Problem’, in Z. W. Pylyshyn (Ed.), The Robot's Dilemma: the frame problem in artificial intelligence pp. 77–94, Norwood: Ablex.Google Scholar
  29. Haugeland, J. (1991), ‘Representational genera’, in W. Ramsey, S.P. Stich, and D.E. Rumelhart (eds.), Philosophy and Connectionist Theory pp. 61–89, Hillsdale: Lawrence Erlbaum Associates.Google Scholar
  30. Hayes, P.J. (1991), Commentary on ‘The Frame Problem: Artificial Intelligence Meets David Hume’, in K.M. Ford and P.J. Hayes (eds.), Reasoning Agents in a Dynamic World: the Frame Problem pp. 71–76, London: JAI Press.Google Scholar
  31. Hinton, G.E. (1990), ‘Preface to The Special Issue on Connectionist Symbol Processing’, Artificial Intelligence, 46, 1–4.Google Scholar
  32. Holyoak, K.J. (1991), Symbolic Connectionism: Toward Third-generation Theories of Expertise’, in K.A. Ericsson and J. Smith (eds.), Toward a General Theory of Expertise: Prospects and Limits Cambridge: Cambridge University Press pp. 30–335.Google Scholar
  33. Horgan, T., and Tienson, J. (1996), Connectionism and the Philosophy of Psychology, Cambridge: MIT-Press.Google Scholar
  34. Hummel, J.E., and Holyoak, K.J. (1993), Distributing Structures Over Time, Behavioral and Brain Sciences 16(3), p.464.Google Scholar
  35. Janlert, L.E. (1987), ‘Modelling change — the frame problem’, in Z.W. Pylyshyn (ed.), The Robot's Dilemma: the Frame Problem in Artificial Intelligence, Norwood: Ablex, pp. 1–40.Google Scholar
  36. Jorna, R.J., and Haselager, W.F.G. (1994), ‘Associationism: Not the Cliff Over Which to Push Connectionism’, The Journal of Intelligent Systems, 4(3–4), pp.297–309.Google Scholar
  37. Kirsh, D. (1990), ‘When is Information Explicitly Represented’, in P. Hanson (ed.), Information, Language, and Cognition, Vancouver: University of British Columbia Press, pp. 340–365.Google Scholar
  38. McCarthy, J., and Hayes, P.J. (1969), ‘Some Philosophical Problems from the Standpoint of Artificial Intelligence’, in B. Meltzer and D. Michie (eds.), Machine Intelligence, Edinburgh: Edinburgh University Press pp.463–502.Google Scholar
  39. McNamara, P. (1993), ‘Introduction’, Philosophical Studies, 71, pp.113–118.Google Scholar
  40. Meyering, T.C. (1993), ‘Neuraal Vernuft en Gedachteloze Kennis: Het Moderne Pleidooi Voor een Niet-propositioneel Kennismodel’, Algemeen Nederlands Tijdschrift voor Wijsbegeerte, 85, pp.24–48.Google Scholar
  41. Miikkulainen, R. and Dyer, M.G. (1991), ‘Natural Language Processing with Modular PDP networks and Distributed Lexicon’. Cognitive Science, 15, pp. 343–399.Google Scholar
  42. Niklasson, L.F., and Van Gelder, T. (1994), ‘On being systematically connectionist’, Mind and Language, 9(3), pp.288–302.Google Scholar
  43. Palmer, S.E. (1978), ‘Fundamental Aspects of Cognitive Representation’, in E. Rosch and B.B. Lloyd (eds.), Cognition and Categorisation, Hillsdale: Erlbaum, pp.259–303.Google Scholar
  44. Pollack, J.B. (1990), ‘Recursive Distributed Representations’, Artificial Intelligence, 46, 77–105.Google Scholar
  45. Pylyshyn, Z.W. (ed.), (1987), The Robot's Dilemma, Norwood: ABLEX Publishing Corporation.Google Scholar
  46. Shanahan, M. (1997), Solving the Frame Problem: A Mathematical Investigation of the Common Sense Law of Inertia, Cambridge: MIT-Press.Google Scholar
  47. Shastri, L. and Ajjanagadde, V. (1993) ‘From Simple Associations to Systematic Reasoning: A Connectionist Representation of Rules, Variables and Dynamic Bindings Using Temporal Synchrony’. Behavioral and Brain Sciences, 16(3), 417–494.Google Scholar
  48. Smolensky, P. (1991), ‘The Constituent Structure of Connectionist Mental States: A Reply to Fodor and Pylyshyn’, in T. Horgan and J. Tienson (eds.), Connectionism and the Philosophy of Mind, Dordrecht: Kluwer Academic Publishers, pp. 281–308.Google Scholar
  49. Sun, R. (1994), ‘Connectionist Models of Commonsense Reasoning’. In D.S. Levine and M.I. Aparicio (eds.), Neural Networks for Knowledge Representation and Inference, Hillsdale: Lawrence Erlbaum Associates, pp. 241–268.Google Scholar
  50. Thagard, P. (1992), Conceptual Revolutions, Princeton: Princeton University Press.Google Scholar
  51. Van Gelder, T. (1990), ‘Compositionality: A Connectionist Variation on a Classical Theme’, Cognitive Science, 14, pp.355–384.Google Scholar
  52. Van Gelder, T. (1991a), ‘Classical Questions, Radical Answers: Connectionism and the Structure of Mental Representation’, in T. Horgan and J. Tienson (eds.), Connectionism and the Philosophy of Mind, Dordrecht: Kluwer Academic Publishers, pp. 355–381.Google Scholar
  53. Van Gelder, T. (1991b), ‘What is the in “PDP”? A Survey of the Concept of Distribution’, In W. Ramsey, S.P. Stich, and D. E. Rumelhart (eds.), Philosophy and Connectionist Theory, Hillsdale: Lawrence Erlbaum Associates, pp. 33–59.Google Scholar
  54. Van Gelder, T. (1992), Defining ‘distributed representation’, Connection Science, 4(3and4), 175–191.Google Scholar
  55. Wilks, Y. (1990), ‘Some comments on Smolensky’, in D. Patridge and Y. Wilks (eds.), The foundations of Al, Cambridge: Cambridge University Press, pp. 327–336.Google Scholar

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

Personalised recommendations