Bidirectional associative memories, self-organizing maps and k-winners-take-all: uniting feature extraction and topological principles

Authors:
Sylvain Chartier;Gyslain Giguère;Dominic Langlois;Rana Sioufi
Affiliations:
School of Psychology, University of Ottawa, Ottawa, ON, Canada;Département d'informatique, Université du Québec à Montréal, Montréal, QC, Canada;School of Psychology, University of Ottawa, Ottawa, ON, Canada;School of Psychology, University of Ottawa, Ottawa, ON, Canada
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 1

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Dynamic heteroassociative neural memories

Neural Networks
On the K-winners-take-all-network

Advances in neural information processing systems 1
Principal component neural networks: theory and applications

Principal component neural networks: theory and applications
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Learning to Predict by the Methods of Temporal Differences

Machine Learning
Neural networks letter: Energy minimization in the nonlinear dynamic recurrent associative memory

Neural Networks
NDRAM: nonlinear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns

IEEE Transactions on Neural Networks
A bidirectional heteroassociative memory for binary and grey-level patterns

IEEE Transactions on Neural Networks

2009 Special Issue: A new bidirectional heteroassociative memory encompassing correlational, competitive and topological properties

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a network combining k-Winners-Take-All and Self-Organizing Map principles within a Feature Extracting Bidirectional Associative Memory. When compared with its "strictly winner-take-all" version, the modified model shows increased performance for clustering, by producing a better weight distribution and a lower dispersion level (higher density) for each given category. Moreover, because the model is recurrent, it is able to develop prototype representations strictly from exemplar encounters. Finally, just like any recurrent associative memory, the model keeps its reconstructive memory and noise filtering properties.