Dynamic learning algorithm of multi-layer perceptrons for letter recognition
作者： Qin Feng , Gao Daqi
DOI: 10.1109/IJCNN.2013.6706896
关键词: Contextual image classification 、 Data set 、 Perceptron 、 Boundary (topology) 、 Algorithm 、 Pattern recognition 、 Computer science 、 Artificial neural network 、 Computational complexity theory 、 Decision boundary 、 Artificial intelligence 、 Backpropagation
摘要: The classical back-propagation learning algorithms of neural networks suffer from a major disadvantage that excessive computational burden encountered by processing all the data. Relatively speaking, samples near separating boundary have more important influent on final weights than those far. This paper presents dynamic algorithm which is just based decision samples. using to update can not only greatly improve speed, but also classification correction. experimental results for Letter data set verified proposed method effective. It far faster and gets 91.1%
sci-hub.se 参考文章(13)
Pomerleau, Gusciora, Touretzky, Kung, Neural network simulation at Warp speed: how we got 17 million connections per second IEEE 1988 International Conference on Neural Networks. pp. 143- 150 ,(1988) , 10.1109/ICNN.1988.23922
Arai, Mapping abilities of three-layer neural networks international joint conference on neural network. pp. 419- 423 ,(1989) , 10.1109/IJCNN.1989.118598
Gao Daqi, Yang Genxing, Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks Pattern Recognition. ,vol. 36, pp. 869- 878 ,(2003) , 10.1016/S0031-3203(02)00120-6
Fritz Stäger, Mukul Agarwal, Three methods to speed up the training of feedforward and feedback perceptrons Neural Networks. ,vol. 10, pp. 1435- 1443 ,(1997) , 10.1016/S0893-6080(97)00053-1
Gao Daqi, Li Chunxia, Yang Yunfan, Task decomposition and modular single-hidden-layer perceptron classifiers for multi-class learning problems Pattern Recognition. ,vol. 40, pp. 2226- 2236 ,(2007) , 10.1016/J.PATCOG.2007.01.002
Chidanand Apté, Fred Damerau, Sholom M. Weiss, Automated learning of decision rules for text categorization ACM Transactions on Information Systems. ,vol. 12, pp. 233- 251 ,(1994) , 10.1145/183422.183423
M. Gori, F. Scarselli, Are multilayer perceptrons adequate for pattern recognition and verification IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 20, pp. 1121- 1132 ,(1998) , 10.1109/34.730549
G. Cybenko, Approximation by superpositions of a sigmoidal function Mathematics of Control, Signals, and Systems. ,vol. 2, pp. 303- 314 ,(1989) , 10.1007/BF02551274
A.K. Jain, P.W. Duin, Jianchang Mao, Statistical pattern recognition: a review IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 22, pp. 4- 37 ,(2000) , 10.1109/34.824819
M. Riedmiller, H. Braun, A direct adaptive method for faster backpropagation learning: the RPROP algorithm IEEE International Conference on Neural Networks. ,vol. 1, pp. 586- 591 ,(1993) , 10.1109/ICNN.1993.298623