Discrete Affine Wavelet Transforms For Anaylsis And Synthesis Of Feedfoward Neural Networks
Discrete Affine Wavelet Transforms For Anaylsis And Synthesis Of Feedfoward Neural Networks
复制标题
前馈神经网络分析与综合的离散仿射小波变换
DOI：
--
复制
发表时间：
1990
期刊：
影响因子：
--
通讯作者：
P. Krishnaprasad
中科院分区：
文献类型：
--
作者：
Y. C. Pati;P. Krishnaprasad
本文证明离散仿射小波变换可以为标准前馈神经网络的分析和综合提供一种工具。证明了L2（IR）的小波帧可以基于s型构造。利用小波的空间-频谱定位特性，可以确定前馈网络的拓扑结构和权重。训练使用这里描述的综合过程构建的网络涉及凸代价函数的最小化，因此避免了标准反向传播算法固有的缺陷。本文还讨论了这些方法在L2（IRN）中的推广。
In this paper we show that discrete affine wavelet transforms can provide a tool for the analysis and synthesis of standard feedforward neural networks. It is shown that wavelet frames for L2(IR) can be constructed based upon sigmoids. The spatia-spectral localization property of wavelets can be exploited in defining the topology and determining the weights of a feedforward network. Training a network constructed using the synthesis procedure described here involves minimization of a convex cost functional and therefore avoids pitfalls inherent in standard backpropagation algorithms. Extension of these methods to L2(IRN) is also discussed.