|
自动化学报 1998
Wavelet Neural Network for Function Learning
|
Abstract:
In identification of nonlinear system,the network inputs usually are multivariab les.The approach using wavelets alone to resolve the problem is complex.Therefore,the paper establishes a new network method by combining neural network and wav elet characteristics to handle the multivariable problem simply and effectively. This paper also gives the mathematical verification that the network can approxi mate any kind of functions.The simulation results of an examkple indicate the validity of the method.