Recurrent neural networks with chaos for storing and retrieving information

Author

Dmitriev, Alexandr S. ; Kuminov, Dmitry A.

Author_Institution

Inst. of Radio Eng. & Electron., Acad. of Sci., Moscow, Russia

fYear

1995

fDate

20-23 Sep 1995

Firstpage

24

Lastpage

31

Abstract

The models studied in this report allow realization of a set of basic functions of information processing using chaos and complex dynamics, such as: storing and retrieving information;. realization of associative memory; image recognition based on the use of storing on unstable cycles. The discussed models should be noted for their considerable information capacity and high computational efficiency along with a limited number of interconnections

Keywords

chaos; content-addressable storage; image recognition; limit cycles; recurrent neural nets; associative memory; chaos; complex dynamics; high computational efficiency; image recognition; information capacity; information processing; information retrieval; information storage; recurrent neural networks; unstable cycles; Artificial neural networks; Chaos; Image retrieval; Information retrieval; Limit-cycles; Mathematical model; Neural network hardware; Neural networks; Piecewise linear techniques; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neuroinformatics and Neurocomputers, 1995., Second International Symposium on

Conference_Location

Rostov on Don

Print_ISBN

0-7803-2512-5

Type

conf

DOI

10.1109/ISNINC.1995.480896

Filename

480896