Regressor selection and wavelet network construction
Qinghua Zhang · 2002
The wavelet network has been introduced as a special feedforward neural network supported by the wavelet theory. In this paper the construction of feedforward neural networks is discussed from the regressor selection point of view. This reveals that the wavelet network structure is well suited for developing constructive methods of feedforward networks. An efficient construction procedure of the wavelet network based on the orthogonal least squares method is then proposed.>