A sequential dynamic heteroassociative memory for multistep pattern recognition and one-to-many association

Authors:
S. Chartier;M. Boukadoum
Affiliations:
Dept. of Psychol., Univ. du Quebec, Montreal, Que, Canada;-
Venue:
IEEE Transactions on Neural Networks
Year:
2006

Citing 0
Cited 5

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

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

Neural Networks
Spatio-temporal memories for machine learning: a long-term memory organization

IEEE Transactions on Neural Networks
BAM learning of nonlinearly separable tasks by using an asymmetrical output function and reinforcement learning

IEEE Transactions on Neural Networks
Multi-wheel graph neuron: a distributed associative memory for structured P2P networks

Proceedings of the 11th International Conference on Information Integration and Web-based Applications & Services

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bidirectional associative memories (BAMs) have been widely used for auto and heteroassociative learning. However, few research efforts have addressed the issue of multistep vector pattern recognition. We propose a model that can perform multi step pattern recognition without the need for a special learning algorithm, and with the capacity to learn more than two pattern series in the training set. The model can also learn pattern series of different lengths and, contrarily to previous models, the stimuli can be composed of gray-level images. The paper also shows that by adding an extra autoassociative layer, the model can accomplish one-to-many association, a task that was exclusive to feedforward networks with context units and error backpropagation learning.