Graduate studies at Western
Minds and Machines 3 (3):253-70 (1993)
|Abstract||The article criticises the attempt to establish connectionism as an alternative theory of human cognitive architecture through the introduction of thesymbolic/subsymbolic distinction (Smolensky, 1988). The reasons for the introduction of this distinction are discussed and found to be unconvincing. It is shown that thebrittleness problem has been solved for a large class ofsymbolic learning systems, e.g. the class oftop-down induction of decision-trees (TDIDT) learning systems. Also, the process of articulating expert knowledge in rules seems quite practical for many important domains, including common sense knowledge.The article discusses several experimental comparisons betweenTDIDT systems and artificial neural networks using the error backpropagation algorithm (ANNs usingBP). The properties of one of theTDIDT systemsID3 (Quinlan, 1986a) are examined in detail. It is argued that the differences in performance betweenANNs usingBP andTDIDT systems reflect slightly different inductive biases but are not systematic; these differences do not support the view that symbolic and subsymbolic systems are fundamentally incompatible. It is concluded, that thesymbolic/subsymbolic distinction is spurious. It cannot establish connectionism as an alternative cognitive architecture|
|Keywords||Artificial Intelligence Connectionism Metaphysics Symbolic Smolensky, P|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Jerry A. Fodor & Brian P. McLaughlin (1990). Connectionism and the Problem of Systematicity: Why Smolensky's Solution Doesn't Work. Cognition 35:183-205.
Paul Smolensky (1995). Constituent Structure and Explanation in an Integrated Connectionist/Symbolic Cognitive Architecture. In C. Macdonald (ed.), Connectionism: Debates on Psychological Explanation. Blackwell.
Axel Cleeremans (1998). The Other Hard Problem: How to Bridge the Gap Between Subsymbolic and Symbolic Cognition. Behavioral and Brain Sciences 21 (1):22-23.
Stevan Harnad (1992). Connecting Object to Symbol in Modeling Cognition. In A. Clark & Ronald Lutz (eds.), Connectionism in Context. Springer-Verlag.
Paul Smolensky (1987). Connectionist, Symbolic, and the Brain. AI Review 1:95-109.
Ron Sun, Beyond Simple Rule Extraction: The Extraction of Planning Knowledge From Reinforcement Learners.
John R. Anderson & Christian Lebiere (2003). The Newell Test for a Theory of Cognition. Behavioral and Brain Sciences 26 (5):587-601.
Andy Clark (1993). Superpositional Connectionism: A Reply to Marinov. [REVIEW] Minds and Machines 3 (3):271-81.
Paul Smolensky (1988). On the Proper Treatment of Connectionism. Behavioral and Brain Sciences 11:1-23.
Istvan S. N. Berkeley (2000). What the #$*%! Is a Subsymbol? Minds and Machines 10 (1):1-13.
Added to index2009-01-28
Total downloads21 ( #65,382 of 733,136 )
Recent downloads (6 months)1 ( #61,087 of 733,136 )
How can I increase my downloads?