A wavelet neural network with network optimizing function
A wavelet neural network with network optimizing function
复制标题
一种具有网络优化功能的小波神经网络
DOI：
10.1002/scj.4690260906
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
N. Yoshida
中科院分区：
文献类型：
--
作者：
K. Kobayashi;T. Torioka;N. Yoshida
提出了一种结合小波和神经网络的新型映射网络。该网络具有三大特点，即神经网络的自构建、近似映射的部分检索和高效学习。网络学习算法大致可分为自构造过程和误差最小化过程。在第一个过程中，隐藏单元以这样的方式串行附加，使得网络结构充分逼近逼近目标。同时，网络参数通过竞争学习进行更新。在第二个过程中，通过局部反向传播算法更新网络参数，直到达到所需的近似精度。通过计算机模拟证明了所提出网络的有效性。
A new mapping network combining wavelets and neural networks is proposed. The proposed network has three major characteristics, namely, self-construction of neural networks, partial retrieval of the approximate mapping, and efficient learning. The network learning algorithm can be divided roughly into the self-construction process and the error minimization process. In the first process, hidden units are appended serially in such a way that the network structure sufficiently approximates the approximation target. Simultaneously, network parameters are updated by competitive learning. In the second process, network parameters are updated by a localized backpropagation algorithm until the desired approximation accuracy is attained. The effectiveness of the proposed network is demonstrated through computer simulations.