文章提出一种基于多分辨率学习的正交基小波神经网络结构的设计方法，网络权值的学习采用阻尼递推最小二乘算法。
A designing method of wavelet neural network structure based on multiresolution learning is put forward, and the studies of network weights adopt damped least squares.
良好的局部放大特性和多分辨率学习特性使得小波神经网络比神经网络有更强的自适应能力、更快的收敛速度和更高的预报精度。
The good local amplification and multi-resolution characteristic make the wavelet network have strong adaptive capacity, fast convergence speed and high precision of prediction.
提出一种基于二进小波变换与多层分组神经网络的自由手写体数字的多分辨率识别算法。
In this paper, a new scheme of multiresolution recognition of unconstrained handwritten numerals based on dyadic wavelet transform and multilayer cluster neural network is presented.
由于小波变换在时间和频率空间具有良好的定位特性，使小波神经网络可对输入、输出数据进行多分辨的学习训练。
The good localization characteristics of wavelet functions in both time and frequency space allow hierarchical multi-resolution learning of input-output data mapping.
提出一种基于正交基函数的小波神经网络设计方法，采用多分辨率学习确定隐含层结构，并用收敛较快的阻尼最小二乘法训练权值。
In this approach the network structure is determined by multiresolution learning, and the weights are trained by damped least squares which has fast convergent rate.
提出一种基于正交基函数的小波神经网络设计方法，采用多分辨率学习确定隐含层结构，并用收敛较快的阻尼最小二乘法训练权值。
In this approach the network structure is determined by multiresolution learning, and the weights are trained by damped least squares which has fast convergent rate.
应用推荐