Initialisation and training procedures for wavelet networks applied to chaotic time series
Wavelet networks are a class of neural network that take advantage of good localization properties of multi-resolution analysis and combine them with the approximation abilities of neural networks. This kind of networks uses wavelets as activation functions in the hidden layer and a type of back-pro...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2010 |
| País: | México |
| Institución: | Instituto Nacional de Astrofísica, Óptica y Electrónica |
| Repositorio: | Repositorio Institucional del INAOE |
| Idioma: | inglés |
| OAI Identifier: | oai:inaoe.repositorioinstitucional.mx:1009/1499 |
| Acceso en línea: | http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/1499 |
| Access Level: | acceso abierto |
| Palabra clave: | info:eu-repo/classification/Wavelet networks/Wavelet networks info:eu-repo/classification/Wavelets/Wavelets info:eu-repo/classification/Approximation theory/Approximation theory info:eu-repo/classification/Multi-resolution analysis/Multi-resolution analysis info:eu-repo/classification/Chaotic time series/Chaotic time series info:eu-repo/classification/cti/1 info:eu-repo/classification/cti/22 info:eu-repo/classification/cti/2203 |
| Sumario: | Wavelet networks are a class of neural network that take advantage of good localization properties of multi-resolution analysis and combine them with the approximation abilities of neural networks. This kind of networks uses wavelets as activation functions in the hidden layer and a type of back-propagation algorithm is used for its learning. However, the training procedure used for wavelet networks is based on the idea of continuous differentiable wavelets and some of the most powerful and used wavelets do not satisfy this property. In this paper we report an algorithm for initialising and training wavelet networks applied to the approximation of chaotic time series. The proposed algorithm which has its foundations on correlation analysis of signals allows the use of different types of wavelets, namely, Daubechies, Coiflets, and Symmlets. To show this, comparisons are made for chaotic time series approximation between the proposed approach and the typical wavelet network. |
|---|