[1]ZHANG Mina,HAN Honggui,QIAO Junfei.Research on dynamic feedforward neural network structure based on growing and pruning methods[J].CAAI Transactions on Intelligent Systems,2011,6(2):101-106.
Copy

Research on dynamic feedforward neural network structure based on growing and pruning methods

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 6 Number of periods: 2011 2 Page number: 101-106 Column: 学术论文—机器学习 Public date: 2011-04-25
Title:
Research on dynamic feedforward neural network structure based on growing and pruning methods
Author(s):
ZHANG Mi’na;  HAN Honggui;  QIAO Junfei 
College of Electronic and Control Engineering, Beijing University of Technology, Beijing 100124， China
Keywords:
adaptive growing and pruning (AGP);  BOD softmeasurement;  neural network;  self organization
CLC:
TP183
DOI:
-
Abstract:
Due to the unchangable online problem of hidden neurons in feedforward neural networks, an adaptive growing and pruning algorithm (AGP) was presented in this paper. This algorithm can insert and prune hidden neurons during the training process to adjust the structure of the network and achieve self organization of neural network structure, which can improve the performance of the neural network. Additionally, this algorithm has been applied to the biochemical oxygen demand (BOD) soft measurement of the wastewater treatment process. Experimental results show that the proposed algorithm can forecast the effluent BOD with better generalization ability and higher accuracy than other selforganizing neural networks.
References:
［1］乔俊飞, 张颖. 一种多层前馈神经网络的快速修剪算法［J］. 智能系统学报, 2008, 3(2): 173176.
QIAO Junfei, ZHANG Ying. Fast unit pruning algorithm for multilayer feedforward network design［J］.CAAI Transactions on Intelligent Systems, 2008, 3(2): 173176. 
［2］杨慧中,王伟娜. 神经网络的两种结构优化算法研究［J］. 信息与控制, 2006, 35(6): 700704.
YANG Huizhong, WANG Weina. Two structure optimization algorithms for neural networks［J］. Information and Control, 2006, 35(6): 700704. 
［3］BORTRMAN M, ALADIEM M. A growing and pruning method for radial basis function networks［J］. IEEE Transaction on Neural Networks, 2009, 20(6): 10391045.
［4］HASSIBI B， STORK D G. Second order derivatives for network pruning: optimal brain surgeon［C］//Advances in Neural Information Processing Systems. San Mateo, USA: Morgan Kauffman, 1993： 164171.
［5］LAURET P, FOCK E, MARA T A. A node pruning algorithm based on a Fourier amplitude sensitivity test method［J］. IEEE Transactions on Neural Networks, 2006, 17 (2): 273293.
［6］ XU Jinhua, DANIEL W. A new training and pruning algorithm based on node dependence and Jacobian rank deficiency［J］. Neurocomputing, 2006, 70(1): 544558.
［7］MARSLAND S, SHAPIRO J. A selforganizing network that grows when required［J］. Neural Networks, 2002, 15(8):10411058.
［8］ISLAM M, SATTAR A, AMIN F, YAO Xin. A new adaptive merging and growing algorithm for designing artificial neural networks［J］. IEEE Trans Systems, Man, CyberneticsPart B: Cybernetics, 2009, 39(3): 705722.
［9］QIAO Junfei, HAN Honggui. A repair algorithm for RBF neural network and its application to chemical oxygen demand modeling［J］. International Journal of Neural Systems, 2010, 20(1): 6374.
［10］JOHNSON C, VENAYAGAMOORTHY G K, MITRA P. Comparison of a spiking neural network and an MLP for robust identification of generator dynamics in a multimachine power system［J］. Neural Networks, 2009, 22(5/6): 833841. 
［11］ RUMELHART D E, HINTON G E,WILLIAMS R J. Learning internal representations by error propagation［M］.Parallel Distributed Processing. Cambridge,USA: MIT Press, 1986： 318362.
［12］韩红桂, 甑博然, 乔俊飞. 动态结构优化神经网络及其在溶解氧控制中的应用［J］. 信息与控制, 2010, 39(3): 354360.
HAN Honggui, ZHEN Boran, QIAO Junfei.Dynamic structure optimization neural network and its applications to dissolved oxygenic (DO) control［J］. Information and Control, 2010, 39(3): 345360. 
［13］PENG Jianxun,LI Kang, HUANG Deshuang. A hybrid forward algorithm for RBF neural network construction［J］. IEEE Transactions on Neural Networks, 2006, 17 (6): 14391451.
Similar References:

Memo

-

Last Update: 2011-05-19

Copyright © CAAI Transactions on Intelligent Systems