A preliminary study on negative correlation learning via correlation-corrected data (NCCD)

被引:24
作者
Chan, ZSH [1 ]
Kasabov, N [1 ]
机构
[1] Univ Auckland, Knowledge Engn & Discovery Res Inst, Auckland 1, New Zealand
关键词
ensemble learning; learning; negative correlation; parallel computing;
D O I
10.1007/s11063-005-1084-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This letter presents a novel cooperative neural network ensemble learning method based on Negative Correlation learning. It enables easy integration of various network models and reduces communication bandwidth significantly for effective parallel speedup. Comparison with the best Negative Correlation learning method reported demonstrates comparable performance at significantly reduced communication overhead.
引用
收藏
页码:207 / 214
页数:8
相关论文
共 9 条
[1]  
Bishop C. M., 1996, Neural networks for pattern recognition
[2]   LIMITS FOR THE PRECISION AND VALUE OF INFORMATION FROM DEPENDENT SOURCES [J].
CLEMEN, RT ;
WINKLER, RL .
OPERATIONS RESEARCH, 1985, 33 (02) :427-442
[3]  
Cowder R.S., 1990, P 1990 CONN MOD SUMM, P117
[4]   A constructive algorithm for training cooperative neural network ensembles [J].
Islam, M ;
Yao, X ;
Murase, K .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (04) :820-834
[5]   Simultaneous training of negatively correlated neural networks in an ensemble [J].
Liu, Y ;
Yao, X .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1999, 29 (06) :716-725
[6]  
Michie D., 1994, Technometrics, V13, P1
[7]  
Perrone M. P., 1993, Artificial Neural Networks for Speech and Vision, P126
[8]   Making use of population information in evolutionary artificial neural networks [J].
Yao, X ;
Liu, Y .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (03) :417-425
[9]   A new evolutionary system for evolving artificial neural networks [J].
Yao, X ;
Liu, Y .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (03) :694-713