RBF neural networks for classification using new Kernel functions

Authors:
Zhenqiu Liu;Hamparsum Bozdogan
Affiliations:
Community Health Research Group, The University of Tennessee, Knoxville, TN;Department of Statistics, The University of Tennessee, Knoxville, TN
Venue:
Neural, Parallel & Scientific Computations - Special issue: Advances in intelligent systems and applications
Year:
2003

Citing 6
Cited 0

Fat-shattering and the learnability of real-valued functions

Journal of Computer and System Sciences
Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
Bayesian Learning for Neural Networks

Bayesian Learning for Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models

Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models
The Effect of the Input Density Distribution on Kernel-based Classifiers

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a new class of kernel functions and try to combine Kmean, EM, and new kernels together, instead of using linear function, we introduce nonlinear softmax output function and cross entropy error function into RBF networks. The resulting network is easy to use, and has favorable classification accuracy. Experiments show that our new model has better performance than traditional RBF neural networks and is super compared with MLP and other nonparametric classification tools.