摘要
以TM图像为例,讨论了基于Levenberg-Marquardt(L-M)算法的BP神经网络分类器及其在遥感图像分类中的应用。LM算法是梯度下降法与高斯牛顿法的结合,由于利用了近似的二阶导数信息,LM算法比梯度法快。就训练次数及准确度而言,LM算法明显优于变学习率法的BP算法。
BP Neural network classifier based on Levenberg-Marquardt (L-M) algorithm and its application to remote sensing image classification is discussed in this paper. L-M algorithm is a combination of gradient method and Gauss-Newton method. With the aid of the approximate second derivative, the L-M algorithm is more efficient than the gradient method. Concerned with the training process and accuracy, the L-M algorithm is superior to varylearning-rate BP method.
出处
《武汉大学学报(信息科学版)》
EI
CSCD
北大核心
2005年第10期928-931,共4页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金资助项目(40228002)
关键词
遥感图像分类
BP神经网络
L-M算法
remote sensing image classification
BP neural network
L-M algorithm