Designing associative memories implemented via recurrent neural networks for pattern recognition

Author

Ruz-Hernandez, J.A. ; Suarez-Duran, M.U. ; Garcia-Hernandez, R. ; Shelomov, E. ; Sanchez, E.N.

Author_Institution

Fac. de Ing., Univ. Autonoma del Carmen, Campeche, Mexico

fYear

2011

fDate

July 31 2011-Aug. 5 2011

Firstpage

2638

Lastpage

2644

Abstract

In this paper a recurrent neural network is used as associative memory for pattern recognition. The goal of associative memory is to retrieve a stored pattern when enough information is presented in the network input. The network is training with twelve bipolar patterns to determine the corresponding weights. The weights are calculated by means of support vector machines training algorithms as the optimal hyperplane and soft margin hyperplane. Once the neural network is trained its performance is evaluated to retrieval stored patterns which correspond to characters encoded as bipolar vectors.

Keywords

content-addressable storage; learning (artificial intelligence); pattern recognition; recurrent neural nets; support vector machines; associative memory design; bipolar pattern; bipolar vectors; network input; neural network training; optimal hyperplane; pattern recognition; recurrent neural network; soft margin hyperplane; stored pattern retrieval; support vector machines training algorithm; Algorithm design and analysis; Associative memory; Pattern recognition; Recurrent neural networks; Support vector machines; Training; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks (IJCNN), The 2011 International Joint Conference on

Conference_Location

San Jose, CA

ISSN

2161-4393

Print_ISBN

978-1-4244-9635-8

Type

conf

DOI

10.1109/IJCNN.2011.6033563

Filename

6033563