Name
Abstract | ||
|---|---|---|
It is well known that single hidden layer feedforward networks with radial basis function (RBF) kernels are universal approximators when all the parameters of the networks are obtained through all kinds of algorithms. However, as observed in most neural network implementations, tuning all the parameters of the network may cause learning complicated, poor generalization, overtraining and unstable. Unlike conventional neural network theories, this brief gives a constructive proof for the fact that a decay RBF neural network with n+1 hidden neurons can interpolate n+1 multivariate samples with zero error. Then we prove that the given decay RBFs can uniformly approximate any continuous multivariate functions with arbitrary precision without training. The faster convergence and better generalization performance than conventional RBF algorithm, BP algorithm, extreme learning machine and support vector machines are shown by means of two numerical experiments. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/TNN.2010.2055888 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
generalization performance,single hidden layer feedforward networks,neural network implementation,radial basis function networks,conventional rbf algorithm,interpolation,decay rbf neural network,function approximation,radial basis function network,decay radial basis function (rbf) neural networks,uniformly approximation,hidden neuron,continuous multivariate function,constructive neural networks,decay rbfs,extreme learning machine,continuous multivariate functions,constructive approximation,conventional neural network theory,bp algorithm,feedforward neural networks,support vector machine,testing,approximation algorithms,radial basis function,support vector machines,neural network,artificial neural networks | Radial basis function network,Feedforward neural network,Radial basis function,Function approximation,Extreme learning machine,Computer science,Support vector machine,Algorithm,Probabilistic neural network,Artificial intelligence,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
21 | 9 | 1941-0093 |
Citations | PageRank | References |
19 | 0.76 | 20 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Muzhou Hou | 1 | 50 | 4.49 |
| Xuli Han | 2 | 159 | 22.91 |