Fuzzy Data Recognition by Polynomial Bidirectional Heteroassociator
COMPSAC '00 24th International Computer Software and Applications Conference
A general framework for fuzzy morphological associative memories
Fuzzy Sets and Systems
A Bidirectional Hetero-Associative Memory for True-Color Patterns
Neural Processing Letters
A New Associative Model with Dynamical Synapses
Neural Processing Letters
Fuzzy associative conjuncted maps network
IEEE Transactions on Neural Networks
A new computational approach for high capacity multiple rule FAMs
ASC '07 Proceedings of The Eleventh IASTED International Conference on Artificial Intelligence and Soft Computing
Permutation-based finite implicative fuzzy associative memories
Information Sciences: an International Journal
Information Sciences: an International Journal
Median hetero-associative memories applied to the categorization of true-color patterns
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part II
Efficiency improvements for fuzzy associative memory
ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
Fuzzy cognitive network: A general framework
Intelligent Decision Technologies
Hi-index | 0.00 |
Kosko's fuzzy associative memory (FAM) is the very first neural network model for implementing fuzzy systems. Despite its success in various applications, the model suffers from very low storage capacity, i.e., one rule per FAM matrix. A lot of hardware and computations are usually required to implement the model and, hence, it is limited to applications with small fuzzy rule-base. In this paper, the inherent property for storing multiple rules in a FAM matrix is identified. A theorem for perfect recalls of all the stored rules is established and based upon which the hardware and computation requirements of the FAM model can be reduced significantly. Furthermore, we have shown that when the FAM model is generalized to the one with max-bounded-product composition, single matrix implementation is possible if the rule-base is a set of semi-overlapped fuzzy rules. Rule modification schemes are also developed and the inference performance of the established high capacity models is reported through a numerical example