期刊文献+

基于L-M算法的BP神经网络分类器 被引量:52

BP Neural Network Classifier Based on Levenberg-Marquardt Algorithm
下载PDF
导出
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
  • 相关文献

参考文献14

  • 1何国金,胡德永.卫星遥感数据的信息论理解[J].地质科技情报,1997,0(S1):44-48. 被引量:3
  • 2Bischof H, Leonardis A. Finding Optimal Neural Networks for Land Use Classification. IEEE Tran. on Geoscience and Remote Sensing,1998,36(1):337~341.
  • 3Muvai H. Remote Sensing Image Analysis Using a Neural Network and Knowledge-based Processing. International Journal of Remote Sensing,1997,18(4):811~828.
  • 4Venkatesh Y V, Raja S K. On the Classification of Multispectral Satellite Images Using the Multilayer Perceptron. Pattern Recognition, 2003,36:2 161~2 175.
  • 5McClellan G E, DeWitt R N, Hemmer T H, et al. Multispectral Image-processing with a Three-layer Back-propagation Network. International Joint Conference on Neural Networks, Washington D C,1989.
  • 6Zhou J, Civco D. Using Genetic Learning Neural Networks for Spatial Decision Making in GIS. Photogrammetric Engineering and Remote Sensing,1996,62(11):1 287~1 295.
  • 7Mas J F . Mapping Land Use/Cover in A Tropical Coastal Area Using Satellite Sensor Data, GIS and Artificial Neural Networks. Estuarine, Coastal and Shelf Science, 2004(59): 219~230.
  • 8司捷,周贵安,李函,韩英铎.基于梯度监督学习的理论与应用(Ⅰ)——基本算法[J].清华大学学报(自然科学版),1997,37(7):71-73. 被引量:26
  • 9赵弘,周瑞祥,林廷圻.基于Levenberg-Marquardt算法的神经网络监督控制[J].西安交通大学学报,2002,36(5):523-527. 被引量:118
  • 10黄豪彩,黄宜坚,杨冠鲁.基于LM算法的神经网络系统辨识[J].组合机床与自动化加工技术,2003(2):6-8. 被引量:43

二级参考文献32

  • 1王春行.液压伺服系统[M].北京:机械工业出版社,1991..
  • 2MartinHaganT HowardDemuthB MarkBealeH 戴葵 等译.Neural Network design [M].北京:机械工业出版社,2002..
  • 3Rumelhart D E, Willians R J. Learning internal representations by error - propagation[M]. In Parallel Distributed Processing,Canbridge, MA MIT Press, 1986.
  • 4Brogan W L. Modern control theory [M] .3nd Ed. Englewood Cliffs, N J: Prentice Hall,1991.
  • 5Neural Network toolbox user's guide. The Math works. Inc. 2000.
  • 6Liu B,IEEE Trans Neural Netw,1994年,5卷,845页
  • 7阎平凡 张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2001..
  • 8Rumelhart D E, Hinton G E, Williams R J. Learninginternal repr esentatio ns by error propagation[A].Rumelhart D E James L.McClelland J L. Parallel di stributed processing: explorations in the microstructure of cognition[C], vol ume 1, Cambridge, MA:MIT Press, 1986.318~362.
  • 9Neural Network Toolbox User's Guide .The Mathworks,inc. 1999.
  • 10Fahlman S E. Faster-learning variations on back-propagation: an e mpirical study[A].Touretzky D,Hinton G,Sejnowski T. Proceedings of the 1988 C onnectionist Models Summer School[C].Carnegic Mellon University,1988,38~51.

共引文献381

同被引文献492

引证文献52

二级引证文献323

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部