𝔖 Bobbio Scriptorium
✦   LIBER   ✦

An Efficient Method to Construct a Radial Basis Function Neural Network Classifier

✍ Scribed by Young-Sup Hwang; Sung-Yang Bang

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
281 KB
Volume
10
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

✦ Synopsis

Radial basis function neural network (RBFN) has the power of the universal function approximation. But how to construct an RBFN to solve a given problem is usually not straightforward. This paper describes a method to construct an RBFN classifier efficiently and effectively. The method determines the middle layer neurons by a fast clustering algorithm and computes the optimal weights between the middle and the output layers statistically. We applied the proposed method to construct an RBFN classifier for an unconstrained handwritten digit recognition. The experiment showed that the method could construct an RBFN classifier quickly and the performance of the classifier was better than the best result previously reported.

πŸ“œ SIMILAR VOLUMES

A wavelet-based radial-basis function ne
A wavelet-based radial-basis function neural network approach to the inverse scattering of conducting cylinders
✍ Ulaş Aşık; Tayfun GΓΌnel; Işın Erer πŸ“‚ Article πŸ“… 2004 πŸ› John Wiley and Sons 🌐 English βš– 149 KB

## Abstract A new approach, based on the radial‐bias function neural network (RBF‐NN) combined with wavelet transform, is presented for the estimation of the locations and radii of conducting cylindrical scatterers. The discrete wavelet transform coefficients of the electric‐field values scattered