Xin Yao's Research Interests: Neural Network Ensembles
Neural network ensembles have been shown to perform better in terms of
generalisation for many problems. I am interested in the issue of how to design
and train a neural network ensemble so that individual networks are
cooperative with each other. The idea is to have different individuals learn
diferent things so that the whole ensemble can learn the overall task better.
In particular, I am keen on negative correlation, boosting and bagging.
Selected Papers
- G. Brown, X. Yao, J. Wyatt, H. Wersing and B. Sendhoff, ``Exploiting
Ensemble Diversity for Automatic Feature Extraction,'' Proc. of the
9th International Conference on Neural Information Processing (ICONIP'02),
pp.1786-1790, Singapore, November 2002.
- Y. Liu and X. Yao, ``Learning and Evolution by Minimization of Mutual
Information,'' Proc. of the 7th International Conference on Parallel
Problem Solving from Nature (PPSN VII), Lecture Notes in Computer Science,
Vol. 2439, Springer, September 2002, pp.495-504.
- Y. Liu, X. Yao, Q. Zhao and T. Higuchi, ``An experimental comparison of
neural network ensemble learning methods on decision boundaries,''
Proceedings of the 2002 International Joint Conference on
Neural Networks (IJCNN'02), pp.221-226, IEEE Press, Piscataway, NJ, USA,
12-17 May 2002.
- X. Yao and Y. Liu, ``From evolving a single neural network to evolving
neural network ensembles,'' In Advances in the Evolutionary Synthesis of
Intelligent Agents, Mukesh J. Patel, Vasant Honavar and Karthik
Balakrishnan (eds.), Chapter 14, pp.383-427, The MIT Press, Cambridge, MA,
2001. (ISBN 0-262-16201-6)
- Y. Liu, X. Yao and T. Higuchi, ``Evolutionary Ensembles with Negative
Correlation Learning,'' IEEE Transactions on Evolutionary
Computation, 4(4):380-387, November 2000.
Available as
TEC391_final.ps.gz.
- Y. Liu and X. Yao, ``Ensemble learning via negative correlation,''
Neural Networks, 12(10):1399-1404, December 1999.
Available as
liu_yao_K98021.ps.gz.
- Y. Liu and X. Yao, ``Simultaneous training of negatively correlated
neural networks in an ensemble,'' IEEE Transactions on
Systems, Man, and Cybernetics, Part B: Cybernetics, 29(6):716-725,
December 1999.
- Y. Liu and X. Yao, ``Negatively correlated neural networks can produce
best ensembles,'' Australian Journal of Intelligent Information
Processing Systems, 4(3/4):176-185, 1997.
Last update: 5 September 2000