Minds and Machines 3 (2):125-153 (1993)
This paper reviews four significant advances on the feedforward architecture that has dominated discussions of connectionism. The first involves introducing modularity into networks by employing procedures whereby different networks learn to perform different components of a task, and a Gating Network determines which network is best equiped to respond to a given input. The second consists in the use of recurrent inputs whereby information from a previous cycle of processing is made available on later cycles. The third development involves developing compressed representations of strings in which there is no longer an explicit encoding of the components but where information about the structure of the original string can be recovered and so is present functionally. The final advance entails using connectionist learning procedures not just to change weights in networks but to change the patterns used as inputs to the network. These advances significantly increase the usefulness of connectionist networks for modeling human cognitive performance by, among other things, providing tools for explaining the productivity and systematicity of some mental activities, and developing representations that are sensitive to the content they are to represent
|Keywords||Connectionism neural networks expert networks recurrent networks RAAM networks|
|Categories||categorize this paper)|
References found in this work BETA
Discovering Complexity Decomposition and Localization as Strategies in Scientific Research.William Bechtel & Robert C. Richardson - 1993 - Princeton.
Citations of this work BETA
Levels of Description and Explanation in Cognitive Science.William P. Bechtel - 1994 - Minds and Machines 4 (1):1-25.
Similar books and articles
The Allure of Connectionism Reexamined.Brian P. McLaughlin & F. Warfield - 1994 - Synthese 101 (3):365-400.
Are Feedforward and Recurrent Networks Systematic? Analysis and Implications for a Connectionist Cognitive Architecture.S. Phillips - 1998 - Philosophical Explorations.
Representational Trajectories in Connectionist Learning.Andy Clark - 1994 - Minds and Machines 4 (3):317-32.
Consciousness, Connectionism, and Cognitive Neuroscience: A Meeting of the Minds.Dan Lloyd - 1996 - Philosophical Psychology 9 (1):61-78.
Connectionism and Cognitive Architecture.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
How Do Connectionist Networks Compute?Gerard O'Brien & Jonathan Opie - 2006 - Cognitive Processing 7 (1):30-41.
Representations Without Rules, Connectionism, and the Syntactic Argument.Kenneth Aizawa - 1994 - Synthese 101 (3):465-92.
PDP Networks Can Provide Models That Are Not Mere Implementations of Classical Theories.Michael R. W. Dawson, D. A. Medler & Istvan S. N. Berkeley - 1997 - Philosophical Psychology 10 (1):25-40.
Added to index2009-01-28
Total downloads26 ( #198,304 of 2,178,178 )
Recent downloads (6 months)1 ( #316,504 of 2,178,178 )
How can I increase my downloads?