Classification and dimensional reduction using restricted radial basis function networks

Radial basis function networks in nonparametric classification and function learning

In this paper we apply normalized radial basis function networks to function learning and in nonparametric classification. A simple parameter learning technique is proposed and convergence and the rates of convergence of the empirically trained networks are studied theoretically and in computer experiments.

Function Emulation Using Radial Basis Function Networks

While learning an unknown input-output task, humans rst strive to understand the qualitative structure of the function. Accuracy of performance is then improved with practice. In contrast, existing neural network function approximators do not have an explicit means for abstracting the qualitative structure of a target function. To ll this gap, we introduce the concept of function emulation, acc...

Universal Approximation Using Radial-Basis-Function Networks

Grade Interpolation Using Radial Basis Function Networks

This paper analyses the application of Radial Basis Function (RBF) networks in grade interpolation. These networks are a very unique member of the family of Artificial Neural Networks. RBF networks have such theoretical properties that establish them as a potential alternative to existing grade interpolation techniques. Their suitability to the problem of grade interpolation will be demonstrate...

Image Compression using Radial Basis Function Networks

In this paper it is proposed an image compression method based on the idea of fitting a set of Neural Networks (NNs) outputs to the image surface, which is a three-dimensional surface where the pixel values are considered as heights (z-values) defined on the x–y ground plane. An image is divided into subimages (blocks) using a quad tree, according to the complexity of the image surface. Individ...