Towards Designing Neural Network Ensembles by Evolution

  title={Towards Designing Neural Network Ensembles by Evolution},
  author={Yong Huan Liu and Xin Yao},
This paper proposes a co-evolutionary learning system, i.e., CELS, to design neural network (NN) ensembles. CELS addresses the issue of automatic determination of the number of individual NNs in an ensemble and the exploitation of the interaction between individual NN design and combination. The idea of CELS is to encourage diierent individual NNs in the ensemble to learn diierent parts or aspects of the training data so that the ensemble can learn the whole training data better. The… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
21 Citations
11 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 21 extracted citations


Publications referenced by this paper.
Showing 1-10 of 11 references

Negatively correlated neural networks can produce best en sembles,

  • Y. Liu, X. Yao
  • Australian Journal of Intelligent Information…
  • 1997
2 Excerpts

How to make best use of evolutionary learning," Complex Systems | From Local Interactions to Global Phenomena

  • X. Yao, Y. Liu, P. Darwen
  • Am sterdam,
  • 1996
2 Excerpts

Neural Networks: A Comprehensive Foundation, Macmillan College

  • S. Haykin
  • Pub lishing Company, Inc.,
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…