Skip to content

Connectionism And Cognitive Architecture A Critical Analysis Essay

  • Allison, L. (1986) A Practical Introduction to Denotational Semantics, Cambridge University Press, Cambridge.Google Scholar

  • Chomsky, N. (1957) Syntactic Structures, Mouton and Company, The Hague.Google Scholar

  • Chomsky, N. (1965) Aspects of the Theory of Syntax, MIT Press, Cambridge, Mass.Google Scholar

  • Feldman, J.A. & Ballard, D.H. (1982) Connectionist Models and their Properties, Cognitive Science6, 205–254.Google Scholar

  • Fodor, J. A. & Pylyshyn, Z. W. (1987) Connectionism and Cognitive Architecture: A Critical Analysis. Cognitive Science Memorandum COGMEM 29, Centre for Cognitive Science, University of Western Ontario, London, Ontario.Google Scholar

  • Mill, J. S. (1843) A System of Logic, vol. 3, Ch. 5; vol. 6, Ch. 2. Longmans, Green and Company, London.Google Scholar

  • Pylyshyn, Z. W. & Demopoulos, W. (eds) (1986) Meaning and Cognitive Structure, Ablex Publishing, Norwood, New Jersey.Google Scholar

  • Rumelhart, D.E. & McClelland, J.L. (1986) PDP Models and General Issues in Cognitive Science. In Rumelhart, McClelland & the PDP Research Group (eds), Parallel Distributed Processing Vol. 1, MIT Press, Cambridge, USA.Google Scholar

  • This paper explores differences between Connectionist proposals for cognitive architecture and the sorts of models that have traditionally been assumed in cognitive science. We claim that the major distinction is that, while both Connectionist and Classical architectures postulate representational mental states, the latter but not the former are committed to a symbol-level of representation, or to a ‘language of thought’: i.e., to representational states that have combinatorial syntactic and semantic structure. Several arguments for combinatorial structure in mental representations are then reviewed. These include arguments based on the ‘systematicity’ of mental representation: i.e., on the fact that cognitive capacities always exhibit certain symmetries, so that the ability to entertain a given thought implies the ability to entertain thoughts with semantically related contents. We claim that such arguments make a powerful case that mind/brain architecture is not Connectionist at the cognitive level. We then consider the possibility that Connectionism may provide an account of the neural (or ‘abstract neurological’) structures in which Classical cognitive architecture is implemented. We survey a number of the standard arguments that have been offered in favor of Connectionism, and conclude that they are coherent only on this interpretation.