Discrete-time cellular neural networks for associative memories: a new design method via iterative learning and forgetting algorithms

Author

Brucoli, Michele ; Carnimeo, Leonarda ; Grassi, Giuseppe

Author_Institution

Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy

Volume

1

fYear

1995

fDate

13-16 Aug 1995

Firstpage

542

Abstract

In this paper a synthesis procedure of discrete-time Cellular Neural Networks (DTCNN´s) for associative memories with iterative learning and forgetting algorithms is developed, by which each pattern to be stored is learnt one at a time and each pattern to be forgotten is deleted one at a time. The proposed approach exploits the properties of pseudo inverse matrices and preserves the local connection feature of DTCNN´s

Keywords

cellular neural nets; content-addressable storage; discrete time systems; iterative methods; learning (artificial intelligence); associative memories; discrete-time cellular neural networks; iterative forgetting algorithms; iterative learning algorithms; local connection feature; pattern forgetting; pattern learning; pseudo inverse matrices; Associative memory; Asymptotic stability; Cellular neural networks; Design methodology; Iterative algorithms; Iterative methods; Large-scale systems; Network synthesis; Sparse matrices; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on

Conference_Location

Rio de Janeiro

Print_ISBN

0-7803-2972-4

Type

conf

DOI

10.1109/MWSCAS.1995.504496

Filename

504496