A self-organizing neural network for nonlinear filtering

Author

Palmieri, Francesco

Author_Institution

Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA

Volume

6

fYear

1992

fDate

10-13 May 1992

Firstpage

2629

Abstract

A neural network based on the combination of a feature map and linear filters is proposed as a generalized adaptive processor for multidimensional nonlinear mapping. The self-organizing part of the system provides a progressively finer embedding of the input space as more units are added to the network. The linear filters, which tap from the memory, provide the function approximations. Learning is achieved with simple rules of the Hebb´s type with no backpropagation needed. Some preliminary results on two-dimensional patterns show the potential of this approach

Keywords

filtering and prediction theory; learning (artificial intelligence); self-organising feature maps; Hebb´s type; feature map; function approximations; generalized adaptive processor; linear filters; multidimensional nonlinear mapping; nonlinear filtering; self-organizing neural network; two-dimensional patterns; Backpropagation; Biological neural networks; Filtering; Function approximation; Least squares approximation; Multidimensional systems; Neural networks; Nonlinear filters; Size control; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on

Conference_Location

San Diego, CA

Print_ISBN

0-7803-0593-0

Type

conf

DOI

10.1109/ISCAS.1992.230681

Filename

230681