HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by O'Reilly, R. C. Search for Related Content PubMed PubMed Citation Articles by O'Reilly, R. C.

Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning

Department of Psychology, University of Colorado at Boulder, Boulder, CO 80309, U.S.A.

Abstract

Computational models in cognitive neuroscience should ideally use biological properties and powerful computational principles to produce behavior consistent with psychological findings. Error-driven backpropagation is computationally powerful and has proven useful for modeling a range of psychological data but is not biologically plausible. Several approaches to implementing backpropagation in a biologically plausible fashion converge on the idea of using bidirectional activation propagation in interactive networks to convey error signals. This article demonstrates two main points about these error-driven interactive networks: (1) they generalize poorly due to attractor dynamics that interfere with the network's ability to produce novel combinatorial representations systematically in response to novel inputs, and (2) this generalization problem can be remedied by adding two widely used mechanistic principles, inhibitory competition and Hebbian learning, that can be independently motivated for a variety of biological, psychological, and computational reasons. Simulations using the Leabra algorithm, which combines the generalized recirculation (GeneRec), biologically plausible, error-driven learning algorithm with inhibitory competition and Hebbian learning, show that these mechanisms can result in good generalization in interactive networks. These results support the general conclusion that cognitive neuroscience models that incorporate the core mechanistic principles of interactivity, inhibitory competition, and error-driven and Hebbian learning satisfy a wider range of biological, psychological, and computational constraints than models employing a subset of these principles.

This article has been cited by other articles:

				C. P. Unsworth and G. Coghill Excessive noise injection training of neural networks for markerless tracking in obscured and segmented environments. Neural Comput., September 1, 2006; 18(9): 2122 - 2145. [Abstract] [Full Text] [PDF]

				K. A. Norman, E. Newman, G. Detre, and S. Polyn How Inhibitory Oscillations Can Train Neural Networks and Punish Competitors Neural Comput., July 1, 2006; 18(7): 1577 - 1610. [Abstract] [Full Text] [PDF]

				S. A. Herd, M. T. Banich, and R. C. O'Reilly Neural Mechanisms of Cognitive Control: An Integrative Model of Stroop Task Performance and fMRI Data J. Cogn. Neurosci., January 1, 2006; 18(1): 22 - 32. [Abstract] [Full Text] [PDF]

				R. C. O'Reilly and M. J. Frank Making Working Memory Work: A Computational Model of Learning in the Prefrontal Cortex and Basal Ganglia Neural Comput., February 1, 2005; 18(2): 283 - 328. [Abstract] [Full Text] [PDF]

				R. Huerta, T. Nowotny, M. Garcia-Sanchez, H. D. I. Abarbanel, and M. I. Rabinovich Learning Classification in the Olfactory System of Insects Neural Comput., August 1, 2004; 16(8): 1601 - 1640. [Abstract] [Full Text] [PDF]

				J. Lucke and C. von der Malsburg Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn Neural Comput., March 1, 2004; 16(3): 501 - 533. [Abstract] [Full Text] [PDF]

				M. W. Spratling and M. H. Johnson Preintegration Lateral Inhibition Enhances Unsupervised Learning Neural Comput., September 1, 2002; 14(9): 2157 - 2179. [Abstract] [Full Text] [PDF]