Wavelet neural networks for function learning
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
This paper proposes a new kind of neural network named varying scales wavelet neural network to reduce wavelet-neuron number and simplify network structure. In order to avoid the local minima, entropy function is used as penalty function. The new network is applied to channel equalization, simulation results demonstrate that this network has less wavelet-neurons and recursive steps and can converge to the global minimum.