Double-Wavelet Neuron Based on Analytical Activation Functions
| Data(s) |
07/12/2009
07/12/2009
2007
|
|---|---|
| Resumo |
In this paper a new double-wavelet neuron architecture obtained by modification of standard wavelet neuron, and its learning algorithm are proposed. The offered architecture allows to improve the approximation properties of wavelet neuron. Double-wavelet neuron and its learning algorithm are examined for forecasting non-stationary chaotic time series. |
| Identificador |
1313-0463 |
| Idioma(s) |
en |
| Publicador |
Institute of Information Theories and Applications FOI ITHEA |
| Palavras-Chave | #Wavelet #Double-Wavelet Neuron #Recurrent Learning Algorithm #Forecasting #Emulation #Analytical Activation Function |
| Tipo |
Article |
