基于小波神经网络的NLAR(p)过程的逼近

Approximating to NLAR(p) with Wavelet Neural Networks

小波神经网络是近年来发展起来的一种逼近非线性函数的新型人工神经网络。特别是,正交尺度函数为基函数的小波神经网络更适合于函数逼近。本文在此基础上讨论了小波神经网络对非线性AR(p)过程的逼近。

Recently, wavelet neural networks have become apopular tool for nonlinear functional approximation. Wavelet neural networks , which basic functions are orthonormal scaling functions, are more suitable in app-roximating to function. Based on it, approximating to NLAR（p） with wavelet neural networks is studied.