Philosophical Psychology 6 (3):305-319 (1993)
Authors |
|
Abstract |
This paper offers both a theoretical and an experimental perspective on the relationship between connectionist and Classical (symbol-processing) models. Firstly, a serious flaw in Fodor and Pylyshyn’s argument against connectionism is pointed out: if, in fact, a part of their argument is valid, then it establishes a conclusion quite different from that which they intend, a conclusion which is demonstrably false. The source of this flaw is traced to an underestimation of the differences between localist and distributed representation. It has been claimed that distributed representations cannot support systematic operations, or that if they can, then they will be mere implementations of traditional ideas. This paper presents experimental evidence against this conclusion: distributed representations can be used to support direct structure-sensitive operations, in a man- ner quite unlike the Classical approach. Finally, it is argued that even if Fodor and Pylyshyn’s argument that connectionist models of compositionality must be mere implementations were correct, then this would still not be a serious argument against connectionism as a theory of mind.
|
Keywords | Cognitivism Compositionality Connectionism Epistemology Fodor, J Pylyshyn, Z |
Categories | (categorize this paper) |
DOI | 10.1080/09515089308573094 |
Options |
![]() ![]() ![]() ![]() |
Download options
References found in this work BETA
Connectionism and Cognitive Architecture: A Critical Analysis.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
Microcognition: Philosophy, Cognitive Science, and Parallel Distributed Processing.Andy Clark - 1989 - MIT Press.
Connectionism and the Problem of Systematicity: Why Smolensky's Solution Doesn't Work.Jerry Fodor & Brian P. McLaughlin - 1990 - Cognition 35 (2):183-205.
Compositionality: A Connectionist Variation on a Classical Theme.Tim van Gelder - 1990 - Cognitive Science 14 (3):355-84.
Recursive Distributed Representations.Jordan B. Pollack - 1990 - Artificial Intelligence 46 (1-2):77-105.
View all 12 references / Add more references
Citations of this work BETA
The Explanatory Role of Computation in Cognitive Science.Nir Fresco - 2012 - Minds and Machines 22 (4):353-380.
View all 23 citations / Add more citations
Similar books and articles
Tensor Products and Split-Level Architecture: Foundational Issues in the Classicism-Connectionism Debate.Marcello Guarini - 1996 - Philosophy of Science 63 (3):S239-S247.
Connectionism, Constituency and the Language of Thought.Paul Smolensky - 1991 - In Barry M. Loewer & Georges Rey (eds.), Meaning in Mind: Fodor and His Critics. Blackwell.
Connectionism and the Language of Thought.Mark Rowlands - 1994 - British Journal for the Philosophy of Science 45 (2):485-503.
Connectionism, Classical Cognitivism and the Relation Between Cognitive and Implementational Levels of Analysis.Keith Butler - 1993 - Philosophical Psychology 6 (3):321-33.
Three-Concept Monte: Explanation, Implementation, and Systematicity.Robert J. Matthews - 1994 - Synthese 101 (3):347-63.
Connectionism and Cognition: Why Fodor and Pylyshyn Are Wrong.James H. Fetzer - 1992 - In A. Clark & Ronald Lutz (eds.), Connectionism in Context. Springer Verlag. pp. 305-319.
Analytics
Added to PP index
2009-01-28
Total views
510 ( #17,074 of 2,499,308 )
Recent downloads (6 months)
17 ( #48,590 of 2,499,308 )
2009-01-28
Total views
510 ( #17,074 of 2,499,308 )
Recent downloads (6 months)
17 ( #48,590 of 2,499,308 )
How can I increase my downloads?
Downloads