Implicative Fuzzy Associative Memories

Author

Sussner, Peter ; Valle, Marcos Eduardo

Author_Institution

Inst. of Math., Stat., & Sci. Comput., State Univ. of Campinas, Sao Paolo

Volume

14

Issue

6

fYear

2006

Firstpage

793

Lastpage

807

Abstract

Associative neural memories are models of biological phenomena that allow for the storage of pattern associations and the retrieval of the desired output pattern upon presentation of a possibly noisy or incomplete version of an input pattern. In this paper, we introduce implicative fuzzy associative memories (IFAMs), a class of associative neural memories based on fuzzy set theory. An IFAM consists of a network of completely interconnected Pedrycz logic neurons with threshold whose connection weights are determined by the minimum of implications of presynaptic and postsynaptic activations. We present a series of results for autoassociative models including one pass convergence, unlimited storage capacity and tolerance with respect to eroded patterns. Finally, we present some results on fixed points and discuss the relationship between implicative fuzzy associative memories and morphological associative memories

Keywords

content-addressable storage; fuzzy neural nets; fuzzy set theory; interconnected systems; fuzzy set theory; implicative fuzzy associative neural memories; interconnected Pedrycz logic neuron; morphological associative memories; pattern association; unlimited storage capacity; Associative memory; Biological system modeling; Convergence; Fuzzy neural networks; Fuzzy set theory; Fuzzy systems; Hebbian theory; Information retrieval; Magnesium compounds; Neural networks; Associative memories; convergence; fuzzy Hebbian learning; fuzzy neural networks; fuzzy relations; fuzzy systems; morphological associative memories; storage capacity; tolerance with respect to noise;

fLanguage

English

Journal_Title

Fuzzy Systems, IEEE Transactions on

Publisher

ieee

ISSN

1063-6706

Type

jour

DOI

10.1109/TFUZZ.2006.879968

Filename

4016092