Connecting Object to Symbol in Modelling Cognition

  • Stevan Harnad
Part of the Artificial Intelligence and Society book series (HCS)


Connectionism and computationalism are currently vying for hegemony in cognitive modelling. At first glance the opposition seems incoherent, because connectionism is itself computational, but the form of computationalism that has been the prime candidate for encoding the “language of thought” has been symbolic computationalism (Dietrich 1990; Fodor 1975; Hamad 1990c; Newell 1980; Pylyshyn 1984), whereas connectionism is non-symbolic (Fodor and Pylyshyn 1988 — or, as some have hopefully dubbed it, “subsymbolic” — Smolensky 1988). This chapter will examine what is and is not a symbol system. A hybrid non-symbolic/symbolic system will be sketched in which the meanings of the symbols are grounded bottom-up in the system’s capacity to discriminate and identify the objects they refer to. Neural nets are one possible mechanism for learning the invariants in the analogue sensory projection on which successful categorization is based. “Categorical perception” (Hamad 1987a), in which similarity space is “warped” in the service of categorization, turns out to be exhibited by both people and nets, and may mediate the constraints exerted by the analogue world of objects on the formal world of symbols.


Categorical Perception Modelling Cognition Symbol System Category Boundary Syntactic Rule 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Berlin B, Kay P (1969) Basic color terms: their universality and evolution. University of California Press, BerkeleyGoogle Scholar
  2. Boynton RM (1979) Human color vision. Holt, Rinehart and Winston, New YorkGoogle Scholar
  3. Cottrell G, Munro P, Zipser D (1987) Image compression by back propagation: an example of extensional programming. ICS Report 8702, Institute for Cognitive Science, UCSDGoogle Scholar
  4. Davis M (1958) Computability and unsolvability. McGraw-Hill, ManchesterMATHGoogle Scholar
  5. Dietrich E (1990) Computationalism. Social Epistemol 4: 135–154CrossRefGoogle Scholar
  6. Elman J, Zipser D (1987) Learning the hidden structure of speech. ICS Report 8701, Institute for Cognitive Science, UCSDGoogle Scholar
  7. Fodor JA (1975) The language of thought. Crowell, New YorkGoogle Scholar
  8. Fodor JA (1985) Pfecis of “The modularity of mind”. Behav Brain Sci 8: 1–42CrossRefGoogle Scholar
  9. Fodor J, Pylyshyn Z (1988) Connectionism and cognitive architecture: a critical analysis. Cognition 28: 3–71CrossRefGoogle Scholar
  10. Gibson EJ (1969) Principles of perceptual learning and development. Prentice Hall, Englewood Cliffs, NJGoogle Scholar
  11. Grossberg SG (1984) Some physiological and pharmacological correlates of a developmental, cognitive, and motivational theory. In: Karrer R, Cohen J, Tueting P (eds) Brain and information: event-related potentials. Ann NY Acad Sci 425: 58–151Google Scholar
  12. Hanson S, Burr D (1990) What connectionist models learn: learning and representation in connectionist networks. Behav Brain Sci 13: 471–518CrossRefGoogle Scholar
  13. Harnad S (1984) Verifying machines’ minds. Contemp Psychol 29: 389–391Google Scholar
  14. Harnad S (ed) (1987a) Categorical perception: the groundwork of cognition. Cambridge University PressGoogle Scholar
  15. Harnad S (1987b) Category induction and representation. In: Harnad S (ed) Categorical perception: the groundwork of cognition. Cambridge University PressGoogle Scholar
  16. Harnad S (1987c) Uncomplemented categories, or, what is it like to be a bachelor. Presidential address, 13th Annual Meeting of the Society for Philosophy and Psychology, UCSDGoogle Scholar
  17. Harnad S (1989) Minds, machines and Searle. J Exp Theor Artif Intell 1: 5–25CrossRefGoogle Scholar
  18. Harnad S (1990a) The symbol grounding problem. Physica D 42: 335–346CrossRefGoogle Scholar
  19. Harnad S (1990b) Lost in the hermeneutic hall of mirrors. J Exp Theor Artif Intell 2: 321–327CrossRefGoogle Scholar
  20. Harnad S (1990c) Commentary on Dietrich’s (1990) “Computationalism”. Social Epistemol 4: 167–172Google Scholar
  21. Harnad S (1990d) Symbols and nets: cooperation vs. competition. Review of: Pinker S, Mehler J (eds) (1988) Connections and symbols. Connection Sci 2: 257–260Google Scholar
  22. Harnad S (1991) Other bodies, other minds: a machine reincarnation of an old philosophical problem. Minds Machines 1: 93–54.Google Scholar
  23. Harnad S, Hanson SJ, Lubin J (1991) Categorical perception and the evolution of supervised learning in neural nets. In: Powers DM, Reeker L (eds) Machine Learning of Natural Language and Ontology (Symposium on Symbol Grounding: Problem and Practice). Working Papers of the American Association for Artificial Intelligence, Spring Symposium, Stanford University, March 1991; reprinted in Deutsches Forschungzentrum fuer Kuenstliche Intelligent Document D-91-09:65-74.Google Scholar
  24. Kleene SC (1969) Formalized recursive functionals, and formalized realizability. Providence, American Mathematical SocietyGoogle Scholar
  25. Lane H (1965) The motor theory of speech perception: a critical review. Psychol Rev 72: 275–309CrossRefGoogle Scholar
  26. Lawrence DH (1950) Acquired distinctiveness of cues: II. Selective association in a constant stimulus situation. J Exp Psychol 40: 175–188CrossRefGoogle Scholar
  27. Lucas J (1961) Minds, machines and Gödel. Philosophy 36: 112–117CrossRefGoogle Scholar
  28. McClelland JL, Rumelhart DE, PDP Research Group (1986) Parallel distributed processing: explorations in the microstructure of cognition, Vol 1. MIT/Bradford, Cambridge, MAGoogle Scholar
  29. Miller GA (1956) The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychol Rev 63: 81–97CrossRefGoogle Scholar
  30. Minsky M, Papert S (1969) Perceptrons: an introduction to computational geometry. MIT Press, Cambridge, MAMATHGoogle Scholar
  31. Newell A (1980) Physical symbol systems. Cognitive Sci 4: 135–183CrossRefGoogle Scholar
  32. Penrose R (1989) The emperor’s new mind. Oxford University PressGoogle Scholar
  33. Penrose R (1990) Précis of: “The emperor’s new mind”. Behav Brain Sci 13: 643–705.CrossRefGoogle Scholar
  34. Pylyshyn ZW (1984) Computation and cognition. Bradford Books, Cambridge, MAGoogle Scholar
  35. Searle JR (1980a) Minds, brains and programs. Behav Brain Sci 3: 417–424CrossRefGoogle Scholar
  36. Searle JR (1980b) Intrinsic intentionality. Behav Brain Sci 3: 450–457CrossRefGoogle Scholar
  37. Shepard RN, Cooper LA (1982) Mental images and their transformations. MIT Press/Bradford, Cambridge, MAGoogle Scholar
  38. Siegel JA, Siegel W (1977) Absolute identification of notes and intervals by musicians. Perception Psychophysics 21: 143–152CrossRefGoogle Scholar
  39. Smolensky P (1988) On the proper treatment of connectionism. Behav Brain Sci 11: 1–74CrossRefGoogle Scholar
  40. Turing AM (1964) Computing machinery and intelligence. In: Anderson A (ed) Minds and machines. Prentice Hall, Englewood Cliffs, NJGoogle Scholar
  41. Tversky A (1977) Features of similarity. Psychol Rev 84: 327–352CrossRefGoogle Scholar
  42. Ullman S (1980) Against direct perception. Behav Brain Sci 3: 373–415CrossRefGoogle Scholar
  43. Wittgenstein L (1953) Philosophical investigations. Macmillan, New YorkGoogle Scholar
  44. Zadeh LA (1965) Fuzzy sets. Information Control 8: 338–353CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1992

Authors and Affiliations

  • Stevan Harnad

There are no affiliations available

Personalised recommendations