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

Authors:
Sylvain Chartier;Gyslain Giguère;Dominic Langlois
Affiliations:
University of Ottawa, School of Psychology, 200 Lees E217, 125 University Street, Ottawa, ON K1N 6N5, Canada;The University of Texas at Austin, Department of Psychology, 1 University Station, A8000, Austin, TX 78712-0187, USA;University of Ottawa, School of Psychology, 200 Lees E217, 125 University Street, Ottawa, ON K1N 6N5, Canada
Venue:
Neural Networks
Year:
2009

Citing 12
Cited 3

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
Neural Networks and Natural Intelligence

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

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Unsupervised learning in noise

IEEE Transactions on Neural Networks
Sensitivity to noise in bidirectional associative memory (BAM)

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

IEEE Transactions on Neural Networks
A sequential dynamic heteroassociative memory for multistep pattern recognition and one-to-many association

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

IEEE Transactions on Neural Networks

A perceptual memory system for affordance learning in humanoid robots

ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
2012 Special Issue: Depth of treatment sensitive noise resistant dynamic artificial neural networks model of recall in people with prosopagnosia

Neural Networks
2011 Special Issue: A hierarchical ART network for the stable incremental learning of topological structures and associations from noisy data

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new recurrent bidirectional model that encompasses correlational, competitive and topological model properties. The simultaneous use of many classes of network behaviors allows for the unsupervised learning/categorization of perceptual patterns (through input compression) and the concurrent encoding of proximities in a multidimensional space. All of these operations are achieved within a common learning operation, and using a single set of defining properties. It is shown that the model can learn categories by developing prototype representations strictly from exposition to specific exemplars. Moreover, because the model is recurrent, it can reconstruct perfect outputs from incomplete and noisy patterns. Empirical exploration of the model's properties and performance shows that its ability for adequate clustering stems from: (1) properly distributing connection weights, and (2) producing a weight space with a low dispersion level (or higher density). In addition, since the model uses a sparse representation (k-winners), the size of topological neighborhood can be fixed, and no longer requires a decrease through time as was the case with classic self-organizing feature maps. Since the model's learning and transmission parameters are independent from learning trials, the model can develop stable fixed points in a constrained topological architecture, while being flexible enough to learn novel patterns.