MODULE COMBINATION BASED ON DECISION TREE IN MIN-MAX MODULAR NETWORK

Yue Wang, Bao-Liang Lu, Zhi-Fei Ye

Abstract

TheMin-Max Modular (M3) Network is the convention solution method to large-scale and complex classification problems. We propose a new module combination strategy using a decision tree for the min-max modular network. Compared with min-max module combination method and its component classifier selection algorithms, the decision tree method has lower time complexity in prediction and better generalizing performance. Analysis of parallel subproblem learning and prediction of these different module combination methods of M3 network show that the decision tree method is easy in parallel.

References

  1. Chu, X., Ma, C., Li, J., Lu, B., Utiyama, M., and Isahara, H. Large-scale patent classification with min-max modular support vector machines. In Proc. of International Joint Conference on Neural Networks, pages 3972- 3977.
  2. Lu, B., Bai, Y., Kita, H., and Nishikawa, Y. (1993). An efficient multilayer quadratic perceptron for pattern classification and function approximation. In Proc. of International Joint Conference on Neural Networks., pages 1385-1388.
  3. Lu, B. and Ito, M. (1999). Task decomposition and module combination based on class relations: A modular neural network for pattern classification. IEEE Transactions on Neural Networks, 10(5):1244-1256.
  4. Lu, B., Shin, J., and Ichikawa, M. (2004). Massively parallel classification of single-trial EEG signals using a min-max modular neural network. IEEE Transactions on Biomedical Engineering, 51(3):551.
  5. Quinlan, J. (1993). C4. 5: programs for machine learning. Morgan Kaufmann.
  6. Vilalta, R. and Drissi, Y. (2002). A perspective view and survey of meta-learning. Artificial Intelligence Review, 18(2):77-95.
  7. Wang, K., Zhao, H., and Lu, B. (2005). Task decomposition using geometric relation for min-max-modular svms. Lecture Notes in Computer Science, 3496:887-892.
  8. Ye, Z. and Lu, B. (2007). Learning Imbalanced Data Sets with a Min-Max Modular Support Vector Machine. In Proc. of International Joint Conference on Neural Networks, pages 1673-1678.
  9. Zhao, H. and Lu, B. (2005). Improvement on response performance of min-max modular classifier by symmetric module selection. Lecture Notes in Computer Science, 3971:39-44.
  10. Zhao, H. and Lu, B. (2006). A modular reduction method for k-nn algorithm with self-recombination learning. Lecture Notes in Computer Science, 3971:537-542.
Download


Paper Citation


in Harvard Style

Wang Y., Lu B. and Ye Z. (2009). MODULE COMBINATION BASED ON DECISION TREE IN MIN-MAX MODULAR NETWORK . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 555-558. DOI: 10.5220/0002319005550558


in Bibtex Style

@conference{icnc09,
author={Yue Wang and Bao-Liang Lu and Zhi-Fei Ye},
title={MODULE COMBINATION BASED ON DECISION TREE IN MIN-MAX MODULAR NETWORK},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={555-558},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002319005550558},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - MODULE COMBINATION BASED ON DECISION TREE IN MIN-MAX MODULAR NETWORK
SN - 978-989-674-014-6
AU - Wang Y.
AU - Lu B.
AU - Ye Z.
PY - 2009
SP - 555
EP - 558
DO - 10.5220/0002319005550558