Neural Processing Letters

, Volume 21, Issue 3, pp 207–214 | Cite as

A Preliminary Study on Negative Correlation Learning via Correlation-Corrected Data (NCCD)



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.


ensemble learning learning negative correlation parallel computing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Clemen, R. T., Winkler, R. L. 1985Limits for the precision and value of information from dependent sourcesOperation Research33427442Google Scholar
  2. 2.
    Perrone, M., Cooper, L. N. 1993When networks disagree: ensemble methods for hybrid neural networksMammone, R. J. eds. Neural Networks for Speech and Image ProcessingChapman & HallLondon, U.KGoogle Scholar
  3. 3.
    Liu, Y., Yao, X. 1999Simultaneous training of negatively correlated neural networks in an ensembleIEEE Transactions on Systems, Man and Cybernetics-Part B: Cybernetics29716725Google Scholar
  4. 4.
    Yao, X. and Liu, Y.: A new evolutionary system for evolving artificial neural networks, IEEE Transactions on Neural Networks 8 (May 1997), 694–713Google Scholar
  5. 5.
    Crowder, R. S.: Predicting the Mackey–Glass time series with cascade-correlation learning, In D. S. T. (ed.), Connectionist Models: Proceedings of the 990 Connectionist Models Summer School, pp. 117–123, 1990Google Scholar
  6. 6.
    Yao, X., Liu, Y. 1998Making use of population information in evolutionary artificial neural networksIEEE Transactions on Systems, Man and Cybernetics-Part B: Cybernetics28417425Google Scholar
  7. 7.
    Michie, D., Spiegelhalter, D. J., Taylor, C. C. 1994Machine Learning, Neural and Statistical ClassificationEllis HorwoodLondon, U.KGoogle Scholar
  8. 8.
    Islam, M., Yao, X., Murase, K. 2003A constructive algorithm for training cooperative neural network ensemblesIEEE Transactions on Neural Networks14820834Google Scholar
  9. 9.
    Bishop, C. 1995Neural Networks for Pattern RecognitionOxford University Press Inc.oxfordGoogle Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  1. 1.Knowledge Engineering and Discovery Research Institute (KEDRI)Auckland University of TechnologyAucklandNew Zealand

Personalised recommendations