Journal of Software:1998.9(4):246-250

高协平,张 钹
Interval-wavelets Neural Networks (ⅠⅠ)——Properties and Experiment
GAO Xie-ping,ZHANG Bo
Chart / table
Similar Articles
Article :Browse 2429   Download 2641
Received:January 21, 1997    Revised:September 01, 1997
> 中文摘要: 证明了区间小波神经网络具有一致及L2逼近性质,且为相容的函数估计子,其学习收敛速度在d维情形不随d增大而减慢,本质上克服了神经网络高维学习的“维数灾难”问题,模拟实例验证了理论的正确性. 关 键 词 神经网络,小波,多尺度分析,收敛.
Abstract:In the present paper, it is proved that the interval wavelets neural networks has universal and L2 approximation properties and is a consistent function estimator. Convergence rates associated with these properties do not decrease as d increases in d-dimensional function learning, i.e., the “curse of dimensionality” is eliminated substantially. In the experiments, the proposed interval wavelet neural networks, compared to traditional wavelet networks, has performed better.
文章编号:     中图分类号:    文献标志码:
基金项目:本文研究得到国家自然科学基金、国家863高科技项目基金和国家攀登计划基金资助. 本文研究得到国家自然科学基金、国家863高科技项目基金和国家攀登计划基金资助.
Foundation items:
Reference text:

高协平,张 钹.区间小波神经网络(ⅠⅠ)——性质与模拟.软件学报,1998,9(4):246-250

GAO Xie-ping,ZHANG Bo.Interval-wavelets Neural Networks (ⅠⅠ)——Properties and Experiment.Journal of Software,1998,9(4):246-250