AI and Society 4 (1):51-71 (1990)
AbstractIn the first section of the article, we examine some recent criticisms of the connectionist enterprise: first, that connectionist models are fundamentally behaviorist in nature (and, therefore, non-cognitive), and second that connectionist models are fundamentally associationist in nature (and, therefore, cognitively weak). We argue that, for a limited class of connectionist models (feed-forward, pattern-associator models), the first criticism is unavoidable. With respect to the second criticism, we propose that connectionist modelsare fundamentally associationist but that this is appropriate for building models of human cognition. However, we do accept the point that there are cognitive capacities for which any purely associative model cannot provide a satisfactory account. The implication that we draw from is this is not that associationist models and mechanisms should be scrapped, but rather that they should be enhanced.In the next section of the article, we identify a set of connectionist approaches which are characterized by “active symbols” — recurrent circuits which are the basis of knowledge representation. We claim that such approaches avoid criticisms of behaviorism and are, in principle, capable of supporting full cognition. In the final section of the article, we speculate at some length about what we believe would be the characteristics of a fully realized active symbol system. This includes both potential problems and possible solutions (for example, mechanisms needed to control activity in a complex recurrent network) as well as the promise of such systems (in particular, the emergence of knowledge structures which would constitute genuine internal models)
Similar books and articles
Representation and computation in a deflationary assessment of connectionist cognitive science.Keith Butler - 1995 - Synthese 104 (1):71-97.
Connectionism and the semantic content of internal representation.T. Goschke & Dirk Koppelberg - 1990 - Review of International Philosophy 44 (172):87-103.
Mother nature versus the walking encyclopedia.Daniel C. Dennett - 1991 - In William Ramsey, Stephen P. Stich & D. Rumelhart (eds.), Philosophy and Connectionist Theory. Lawrence Erlbaum. pp. 21--30.
Experience without the head.Alva Noë - 2006 - In Tamar Gendler & John Hawthorne (eds.), Perceptual Experience. Oxford University Press. pp. 411--433.
Pr cis of connectionism and the philosophy of psychology.Terence Horgan & John Tienson - 1997 - Philosophical Psychology 10 (3):337 – 356.
Added to PP
Historical graph of downloads
Citations of this work
Perceptual symbol systems.Lawrence W. Barsalou - 1999 - Behavioral and Brain Sciences 22 (4):577-660.
A solution to the tag-assignment problem for neural networks.Gary W. Strong & Bruce A. Whitehead - 1989 - Behavioral and Brain Sciences 12 (3):381-397.
What connectionist models learn: Learning and representation in connectionist networks.Stephen José Hanson & David J. Burr - 1990 - Behavioral and Brain Sciences 13 (3):471-489.
The Hebbian paradigm reintegrated: Local reverberations as internal representations.Daniel J. Amit - 1995 - Behavioral and Brain Sciences 18 (4):617-626.
References found in this work
Human Inference: Strategies and Shortcomings of Social Judgment.Richard E. Nisbett & Lee Ross - 1980 - Englewood Cliffs, NJ, USA: Prentice-Hall.
Connectionism and cognitive architecture: A critical analysis.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
Godel, Escher, Bach: An Eternal Golden Braid.Douglas Richard Hofstadter - 1979 - Hassocks, England: Basic Books.
The Nature of Explanation.Kenneth James Williams Craik - 1943 - Cambridge: Cambridge University Press.