Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture
Graduate studies at Western
|Abstract||Human cognition is said to be systematic: cognitive ability generalizes to structurally related behaviours. The connectionist approach to cognitive theorizing has been strongly criticized for its failure to explain systematicity. Demonstrations of generalization notwithstanding, I show that two widely used networks (feedforward and recurrent) do not support systematicity under the condition of local input/output representations. For a connectionist explanation of systematicity, these results leave two choices, either: (1) develop models capable of systematicity under local input/output representations; or (2) justify the choice of similarity-based (nonlocal) component representations sufficient for systematicity.|
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Robert F. Hadley & M. B. Hayward (1997). Strong Semantic Systematicity From Hebbian Connectionist Learning. Minds and Machines 7 (1):1-55.
Steven Phillips (1999). Systematic Minds, Unsystematic Models: Learning Transfer in Humans and Networks. [REVIEW] Minds and Machines 9 (3):383-398.
William Bechtel (1993). Currents in Connectionism. Minds and Machines 3 (2):125-153.
Michael V. Antony (1991). Fodor and Pylyshyn on Connectionism. Minds and Machines 1 (3):321-41.
Jerry A. Fodor & Zenon W. Pylyshyn (1988). Connectionism and Cognitive Architecture. Cognition 28:3-71.
Brian P. McLaughlin (2009). Systematicity Redux. Synthese 170 (2):251 - 274.
Brian P. McLaughlin & F. Warfield (1994). The Allure of Connectionism Reexamined. Synthese 101 (3):365-400.
Paul M. Churchland (1997). To Transform the Phenomena: Feyerabend, Proliferation, and Recurrent Neural Networks. Philosophy of Science 64 (4):420.
William P. Bechtel (1994). Natural Deduction in Connectionist Systems. Synthese 101 (3):433-463.
Added to index2009-01-28
Total downloads6 ( #154,981 of 738,363 )
Recent downloads (6 months)4 ( #20,702 of 738,363 )
How can I increase my downloads?