Synthesis of a nonrecurrent associative memory model based on a nonlinear transformation in the spectral domain

Author

Hunt, B. ; Nadar, Mariappan S. ; Keller, P. ; VonColln, Eric ; Goyal, Anupam

Author_Institution

Dept. of Electr. & Comput. Eng., Arizona Univ., Tucson, AZ, USA

Volume

4

Issue

5

fYear

1993

fDate

9/1/1993 12:00:00 AM

Firstpage

873

Lastpage

878

Abstract

A new nonrecurrent associative memory model is proposed. This model is composed of a nonlinear transformation in the spectral domain followed by the association. The Moore-Penrose pseudoinverse is employed to obtain the least squares optimal solution. Computer simulations are done to evaluate the performance of the model. The simulations use one-dimensional speech signals and two-dimensional head/shoulder images. Comparison of the proposed model with the classical optimal linear associative memory and an optimal nonlinear associative memory is presented

Keywords

content-addressable storage; image processing; least squares approximations; neural nets; spectral-domain analysis; speech analysis and processing; transforms; 1D speech signals; 2D head/shoulder images; Moore-Penrose pseudoinverse; least squares optimal solution; nonlinear transformation; nonrecurrent associative memory model; spectral domain; Associative memory; Computational modeling; Computer simulation; Head; Least squares methods; Neural networks; Nonlinear optics; Optical filters; Speech; Vectors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.248464

Filename

248464