小波神经网络及其应用  

WAVELET NEURAL NETWORK AND ITS APPLICATION

作　　者：蔡念[1] 胡匡祜[1] 李淑宇[1] 苏万芳[1] 

机构地区：[1]中国科学院生物物理研究所,北京100101

出　　处：《中国体视学与图像分析》2001年第4期239-245,共7页Chinese Journal of Stereology and Image Analysis

摘　　要：小波神经网络是将小波理论和神经网络理论结合起来的一种神经网络,它避免了BP神经网络结构设计的盲目性和局部最优等非线性优化问题,大大简化了训练,具有较强的函数学习能力和推广能力及广阔的应用前景。首先阐明了小波变换和多分辨分析理论,然后介绍小波神经网络数学模型和应用概况。Wavelet neural network is a kind of neural networks, which can closely combine wavelet theory with neural network theory, and avoid the blindness of framework designs for BP neural networks and the problem of nonlinear optimizations, such as local optimization. So it can greatly simplify the training of neural networks. It has good abilities of function learning and dissemination with a vast range of prospects for application. The theories of wavelet transformation and multiresolution analysis are expounded, and then the mathematical model for the wavelet neural networks and its applications are introduced.

关 键 词：神经网络 小波神经网络 小波变换 多层多分辨率学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]