Abstract | ||
---|---|---|
In the construction of a Wavelet Neural Network, the number of neurons is determined by the traslation coefficient and by the dilations coefficient. Exists two ways to set the value of the traslation coefficients and dilation, one is considering the coefficients like a hidden layer of the network and the other way is establishing fixed values to those coefficients, where there remains the problem of establishing the number of fixed values to be taken, in this paper we present an algorithm to determine the number of fixed values, that they minimize a rate that depends on the approximation error and the number of neurons that are used. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/IJCNN.2011.6033616 | Neural Networks |
Keywords | Field | DocType |
approximation theory,function approximation,neural nets,optimisation,wavelet transforms,approximation error,dilation coefficient,fixed wavelet neural network optimization,network hidden layer,traslation coefficient | Wavelet neural network,Dilation (morphology),Function approximation,Approximation theory,Artificial intelligence,Artificial neural network,Wavelet packet decomposition,Machine learning,Approximation error,Mathematics,Wavelet transform | Conference |
ISSN | ISBN | Citations |
2161-4393 | 978-1-4244-9635-8 | 1 |
PageRank | References | Authors |
0.36 | 3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Juan Jose Cordova | 1 | 1 | 0.36 |
Wen Yu | 2 | 283 | 22.70 |