Approximate radial basis function neural networks (RBFNN) to learn smooth relations from noisy data

Author

Maffezzoni, Paolo ; Gubian, Paolo

Author_Institution

Department of Electron. Eng., Brescia Univ., Italy

Volume

1

fYear

1994

fDate

3-5 Aug 1994

Firstpage

553

Abstract

In this paper a novel RBFNN scheme is presented introducing the idea of strongly delocalized neural receptive fields. Based on delocalization, a robust deterministic annealing procedure is proposed for determining the RBF centers. It is shown that highly overlapped receptive fields exhibit good noise rejection capability. A real world sensor application of this RBFNN is described. By approximating the exact gaussian fields with a suitable radial function (RF), the forward step of the RBFNN can be efficiently implemented in a single digital chip for real time sensor applications

Keywords

intelligent sensors; learning (artificial intelligence); neural nets; simulated annealing; smoothing methods; data smoothing; delocalization; digital chip; gaussian fields; learning; noise rejection; radial basis function neural networks; real time sensor; receptive fields; robust deterministic annealing; Annealing; Backpropagation; Data engineering; Hardware; Neurons; Noise level; Noise robustness; Radial basis function networks; Radio frequency; Sensor phenomena and characterization;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on

Conference_Location

Lafayette, LA

Print_ISBN

0-7803-2428-5

Type

conf

DOI

10.1109/MWSCAS.1994.519299

Filename

519299