An Internal Report for Connectionists
Although there is a considerable diversity of representational formalisms in the Connectionist literature, most of the excitement about representation has been concerned with the idea of distributed representations. Dissatisfied with the Symbolic tradition, and in search of the new, many cognitive theorists began to infiltrate connectionism in search of a new theory of mind. Like the Classicists, these theorists required that a constructed, analytic theory of mind postulate complex structured representations; it is only by having structural similarities among representations that we can account for the systematic nature of human thought. The Classical view is that the systematic relations between representations are necessarily based on the composition of similar syntactic elements. Likewise, some of the representational types found in the connectionist literature satisfy this requirement, only by virtue of the fact that they are similar to Classically conceived symbolic representations. For example, the structure of complex expression may be maintained in vector frames consisting of explicit tokens or complex expressions that are essentially passed around a net . Only distributed representations offered the promise of a novel representational scheme that could underpin a connectionist theory of cognition; a scheme that relied upon the assumption that structural similarity relations can be captured in a connectionist net by systematic vectorial distances between the distributed representations created.
KeywordsDecision Boundary Hide Unit Output Unit Decision Space Connectionist School
Unable to display preview. Download preview PDF.
- Aizawa, K. (1992) Review of Philosophy and Connectionist Theory. W. Ramsey, S.P. Stich & D.E. Rumelhart (Eds). In Mind and Language, 7.Google Scholar
- Baldwin, A. (1993) The role of connectionist representation in necessary inference for natural language processing. Unpublished PhD. thesis, University of Exeter.Google Scholar
- Chalmers, D.J. (1990) Why Fodor and Pylyshyn were wrong: The simplest refutation. Proceedings of the Twelfth Annual Conference of the Cognitive Science Society, 340–347.Google Scholar
- Elman, J.L. (1989). Representation and structure in connectionist models. CRL Technical Report 8903, Center for Research in Language, University of California, San Diego, CA.Google Scholar
- Fodor, J.A. (1975) The Language of Thought. New York: Crowell.Google Scholar
- van Gelder, T.( 1989) Classical questions, radical answers: Connectionism and the structure of mental representations. Horgan, T. & Tienson J. (Eds) Connectionism and the Philosophy of Mind.Google Scholar
- McDermott, D. (1976) Artificial intelligence meets natural stupidity. SIGART Newsletter, no. 57, 4–9.Google Scholar
- Sharkey, N.E. (1991) Connectionist representation techniques. AI Review, 5,3, 143–167.Google Scholar
- Sharkey, N.E. (1992) The Ghost in the Hybrid: A Study of Uniquely Connectionist Representations. AISB Quarterly. 10–16.Google Scholar
- Sharkey, N.E. & Jackson, S.A. (In press) Three horns of the representational trilemma. In V. Honavar & L. Uhr (Eds) Artificial Intelligence and Neural Networks: Steps towards Principled Integration. Volume 1: Basic Paradigms; Learning Representational Issues; and Integrated Architectures. Cambridge, MA: Academic Press.Google Scholar