Paper Info
Title
An introduction to tunable equivalence fuzzy associative memories
Abstract
In this paper, we present a new class of fuzzy associative memories (FAMs) called tunable equivalence fuzzy associative memories, for short tunable E-FAMs or TE-FAMs, that belong to the class Θ-fuzzy associative memories (Θ-FAMs). Recall that 0-FAMs represent fuzzy neural networks having a competitive hidden layer and weights that can be adjusted via a training algorithm. Like any associative memory model, Θ-FAMs depend on the specification of a fundamental memory set. In contrast to other Θ-FAM models, TE-FAMs make use of parametrized fuzzy equivalence measures that are associated with the hidden nodes and allow for the extraction of a fundamental memory set from the training data. The use of a smaller fundamental memory set than in previous articles on Θ-FAMs reduces the computational effort involved in deriving the weights without decreasing the quality of the results.
Year
DOI
Venue
2014
10.1109/FUZZ-IEEE.2014.6891851
Fuzzy Systems
Keywords
Field
DocType
content-addressable storage,equivalence classes,fuzzy neural nets,fuzzy set theory,learning (artificial intelligence),Θ-FAM,Θ-fuzzy associative memories,TE-FAM,competitive hidden layer,fundamental memory set specification,fuzzy neural networks,training algorithm,training data,tunable equivalence fuzzy associative memories
Neuro-fuzzy,Content-addressable memory,Fuzzy classification,Bidirectional associative memory,Computer science,Fuzzy set operations,Fuzzy logic,Theoretical computer science,Artificial intelligence,Fuzzy associative matrix,Fuzzy number,Machine learning
Conference
ISSN
Citations 
PageRank 
1544-5615
0
0.34
References 
Authors
15
3
Name
Order
Citations
PageRank
Estevão Laureano Esmi19012.01
Peter Sussner288059.25
Sandra Sandri311610.19