A new learning strategy of general BAMs

Authors:
Nong Thi Hoa;Bui The Duy
Affiliations:
Human Machine Interaction Laboratory, Vietnam National University, Hanoi, Vietnam;Human Machine Interaction Laboratory, Vietnam National University, Hanoi, Vietnam
Venue:
MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Year:
2012

Citing 10
Cited 0

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
BAM learning of nonlinearly separable tasks by using an asymmetrical output function and reinforcement learning

IEEE Transactions on Neural Networks
A new bi-directional associative memory

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Improving Leung's bidirectional learning rule for associative memories

IEEE Transactions on Neural Networks
Neural associative memory storing gray-coded gray-scale images

IEEE Transactions on Neural Networks
Encoding strategy for maximum noise tolerance bidirectional associative memory

IEEE Transactions on Neural Networks
Guaranteed recall of all training pairs for bidirectional associative memory

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

IEEE Transactions on Neural Networks
Weighted learning of bidirectional associative memories by global minimization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bi-directional Associative Memory (BAM) is an artificial neural network that consists of two Hopfield networks. The most important advantage of BAM is the ability to recall a stored pattern from a noisy input, which depends on learning process. Between two learning types of iterative learning and non-iterative learning, the former allows better noise tolerance than the latter. However, interactive learning BAMs take longer to learn. In this paper, we propose a new learning strategy that assures our BAM converges in all states, which means that our BAM recalls perfectly all learning pairs. Moreover, our BAM learns faster, more flexibility and tolerates noise better. In order to prove the effectiveness of the model, we have compared our model to existing ones by theory and by experiments.