Bidirectional associative memories
IEEE Transactions on Systems, Man and Cybernetics
Dynamic heteroassociative neural memories
Neural Networks
The cascade-correlation learning architecture
Advances in neural information processing systems 2
Better learning for bidirectional associative memory
Neural Networks
A Bidirectional Associative Memory Based on Optimal Linear Associative Memory
IEEE Transactions on Computers
Associative dynamics in a chaotic neural network
Neural Networks
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Spiking Neuron Models: An Introduction
Spiking Neuron Models: An Introduction
Generalized asymmetrical bidirectional associative memory for multiple association
Applied Mathematics and Computation
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Alpha---Beta bidirectional associative memories: theory and applications
Neural Processing Letters
A general model for bidirectional associative memories
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new synthesis approach for feedback neural networks based on the perceptron training algorithm
IEEE Transactions on Neural Networks
A feedforward bidirectional associative memory
IEEE Transactions on Neural Networks
Encoding strategy for maximum noise tolerance bidirectional associative memory
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Sensitivity to noise in bidirectional associative memory (BAM)
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
A bidirectional heteroassociative memory for binary and grey-level patterns
IEEE Transactions on Neural Networks
Mathematics and Computers in Simulation
A new learning strategy of general BAMs
MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Hi-index | 0.00 |
Most bidirectional associative memory (BAM) networks use a symmetrical output function for dual fixed-point behavior. In this paper, we show that by introducing an asymmetry parameter into a recently introduced chaotic BAM output function, prior knowledge can be used to momentarily disable desired attractors from memory, hence biasing the search space to improve recall performance. This property allows control of chaotic wandering, favoring given subspaces over others. In addition, reinforcement learning can then enable a dual BAM architecture to store and recall nonlinearly separable patterns. Our results allow the same BAM framework to model three different types of learning: supervised, reinforcement, and unsupervised. This ability is very promising from the cognitive modeling viewpoint. The new BAM model is also useful from an engineering perspective; our simulations results reveal a notable overall increase in BAM learning and recall performances when using a hybrid model with the general regression neural network (GRNN).