Learning From Data: General Issues and Special Applications of Radial Basis Function Networks

TitleLearning From Data: General Issues and Special Applications of Radial Basis Function Networks
Publication TypeTechnical Report
Year of Publication1998
AuthorsBaraldi, A., & Borghese N. Alberto
Other Numbers1146
Keywordsactual risk and empirical risk, basis function, constructive network, curse of dimensionality, data-driven and error-driven learning, grid-partitioning and scatter-partitioning network, Hierarchical Radial Basis Function network, hybrid learning, Inductive and deductive types of inference, kernel function, learning from data, Multi-Layer-Perceptron, neural networks, one- and two-stage learning, predictive learning, Radial Basis Function network, supervised and unsupervised learning
Abstract

In the first part of this work some important issues regarding the use of data-driven learning systems are discussed. Next, a special category of learning systems known as artificial Neural Networks (NNs) is presented. Our attention is focused on a specific class of NNs, termed Radial Basis Function (RBF) networks, which are widely employed in classification and function regression tasks. A constructive RBF network, termed Hierarchical RBF (HRBF) model, is proposed. An application where the HRBF model is applied to reconstruct a continuous 3-D surface from range data samples is presented.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1998/tr-98-028.pdf
Bibliographic Notes

ICSI Technical Report TR-98-028

Abbreviated Authors

A. Baraldi and N. A. Borghese

ICSI Publication Type

Technical Report