Structure Pruning Strategies for Min-Max Modular Network | SpringerLink
Skip to main content
Springer Nature Link
Log in

Structure Pruning Strategies for Min-Max Modular Network

  • Conference paper
Advances in Neural Networks – ISNN 2005 (ISNN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3496))

Included in the following conference series:

  • 1455 Accesses

Abstract

The min-max modular network has been shown to be an efficient classifier, especially in solving large-scale and complex pattern classification problems. Despite its high modularity and parallelism, it suffers from quadratic complexity in space when a multiple-class problem is decomposed into a number of linearly separable problems. This paper proposes two new pruning methods and an integrated process to reduce the redundancy of the network and optimize the network structure. We show that our methods can prune a lot of redundant modules in comparison with the original structure while maintaining the generalization accuracy.

This work was supported in part by the National Natural Science Foundation of China via the grants NSFC 60375022 and NSFC 60473040.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Lu, B.L., Ito, M.: Task Decomposition Based on Class Relations: a Modular Neural Network Architecture for Pattern Classification. In: Cabestany, J., Mira, J., Moreno-Díaz, R. (eds.) IWANN 1997. LNCS, vol. 1240, pp. 330–339. Springer, Heidelberg (1997)

    Chapter  Google Scholar 

  2. Lu, B.L., Ito, M.: Task Decomposition and Module Combination Based on Class Relations: a Modular Neural Network for Pattern Classification. IEEE Trans. Neural Networks 10, 1244–1256 (1999)

    Article  Google Scholar 

  3. Lu, B.L., Shin, J., Ichikawa, M.: Massively Parallel Classification of Single-trial EEG Signals Using a Min-Max Modular Neural Network. IEEE Trans. Biomedical Engineering 51, 551–558 (2004)

    Article  Google Scholar 

  4. Lu, B.L., Ichikawa, M.: Emergent On-line Learning in Min-max Modular Neural Networks. In: Proc. of IEEE/INNS Int. Conf. on Neural Networks, Washington DC, USA, pp. 2650–2655 (2001)

    Google Scholar 

  5. Wilson, D.R., Martinez, T.R.: Reduction Techniques for Instance-based Learning Algorithms. Machine Learning 38, 257–286 (2000)

    Article  MATH  Google Scholar 

  6. Lian, H.C., Lu, B.L.: An Algorithm for Pruning Redundant Modules in Min- Max Modular Network. In: Proc. 14th National Conference on Neural Network, pp. 37–42. Hefei University of Technology Press (2004) (in Chinese)

    Google Scholar 

  7. Gates, G.W.: The Reduced Nearest Neighbor Rule. IEEE Transaction on Information Theory IT-18-3, 431–433 (1972)

    Article  Google Scholar 

  8. Blake, C. L., Merz, C. J.: UCI (1998), ftp://ftp.ics.uci.edu/pub/machine-learningdatabases

  9. Lu, B.L., Ichikawa, M.: Emergent Online Learning with a Gaussian Zero-crossing Discriminant Function. In: Proc. IJCNN 2002, pp. 1263–1268 (2002)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Shanghai Jiao Tong University, 1954 Hua Shan Rd., Shanghai, 200030, China

    Yang Yang & Baoliang Lu

Authors
  1. Yang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Baoliang Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China

    Jun Wang

  2. The Key Laboratory of Optoelectric Technology & Systems, Ministry of Education, China

    Xiaofeng Liao

  3. Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, 610054, Chengdu, P.R. China

    Zhang Yi

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yang, Y., Lu, B. (2005). Structure Pruning Strategies for Min-Max Modular Network. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_103

Download citation

  • DOI: https://doi.org/10.1007/11427391_103

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-25912-1

  • Online ISBN: 978-3-540-32065-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics