Connection Science 2:53-62 (1990)
There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of classical symbolic theories. This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations. An experiment is performed using Pollack’s Recursive Auto-Associative Memory. RAAM is used to construct distributed representations of syntactically structured sentences. A feed-forward network is then trained to operate directly on these representations, modeling syn- tactic transformations of the represented sentences. Successful training and generalization is obtained, demonstrating that the implicit structure present in these representations can be used for a kind of structure-sensitive processing unique to the connectionist domain.
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
Toward a Connectionist Model of Recursion in Human Linguistic Performance.Morten H. Christiansen & Nick Chater - 1999 - Cognitive Science 23 (2):157-205.
The Cognizer's Innards: A Psychological and Philosophical Perspective on the Development of Thought.Andy Clark & Annette Karmiloff-Smith - 1994 - Mind and Language 8 (4):487-519.
Conceivability and Possibility: Some Dilemmas for Humeans.Francesco Berto & Tom Schoonen - forthcoming - Synthese:1-19.
The Connectionism/Classicism Battle to Win Souls.Brian P. McLaughlin - 1993 - Philosophical Studies 71 (2):163-190.
Cognitive Systems as Dynamic Systems.Terence E. Horgan & John L. Tienson - 1992 - Topoi 11 (1):27-43.
Similar books and articles
Localist Representations and Theoretical Clarity.Norman D. Cook - 2000 - Behavioral and Brain Sciences 23 (4):474-475.
On the Compatibility of Connectionist and Classical Models.John Hawthorne - 1989 - Philosophical Psychology 2 (1):5-16.
Connectionist Modelling in Psychology: A Localist Manifesto.Mike Page - 2000 - Behavioral and Brain Sciences 23 (4):443-467.
Connectionism and Compositionality: Why Fodor and Pylyshyn Were Wrong.David J. Chalmers - 1993 - Philosophical Psychology 6 (3):305-319.
The Many Ways to Distribute Distributed Representations.A. Mike Burton - 2000 - Behavioral and Brain Sciences 23 (4):472-473.
The Case Against Distributed Representations: Lack of Evidence.Simon Farrell & Stephan Lewandowsky - 2000 - Behavioral and Brain Sciences 23 (4):476-477.
Structure Without Symbols: Providing a Distributed Account of High-Level Cognition.Chris Eliasmith - manuscript
Localist but Distributed Representations.Stephen Grossberg - 2000 - Behavioral and Brain Sciences 23 (4):478-479.
Localist Representations Are a Desirable Emergent Property of Neurologically Plausible Neural Networks.Colin Martindale - 2000 - Behavioral and Brain Sciences 23 (4):485-486.
Added to index2009-01-28
Total downloads123 ( #39,982 of 2,178,142 )
Recent downloads (6 months)1 ( #316,663 of 2,178,142 )
How can I increase my downloads?