Skip to main content
SpringerLink
Log in

A new implementation of the algorithm of adaptive construction of hierarchical neural network classifiers

  • Published:
Optical Memory and Neural Networks Aims and scope Submit manuscript

Abstract

The article presents development of the algorithm of adaptive construction of hierarchical neural network classifiers based on automatic modification of the desired output of perceptrons with a small number of neurons in the single hidden layer. The conducted testing of the new program implementation of this approach demonstrated that the considered algorithm was more computationally efficient and provided higher quality of solution of multiple classification problems in comparison with standard multi-layer perceptron.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Dolenko, S.A., Orlov, Yu.V., Persiantsev, I.G., Shugai, J.S., and Eremin, E.K., Adaptive method of construction of a perceptron-based hierarchical structure of classifiers, The 4th Open Russian-German Workshop on Pattern Recognition and Image Analysis, Valdai, 1996, pp. 45–49.

    Google Scholar 

  2. Dolenko, S.A., Orlov, Yu.V., Persiantsev, I.G., Shugai, Ju.S., and Eremin, E.K., The perceptron-based hierarchical structure of classifiers constructed by the adaptive method, Pat. Rec. Image Analysis, 1997, vol. 7, no. 1, pp. 24–28.

    Google Scholar 

  3. Dolenko, S.A., Orlov, Yu.V., Persiantsev, I.G., Shugai, Ju.S., and Eremin, E.K., Self-organizing construction of hierarchical structure of multi-layer perceptrons, Proceedings Fifth Int. Conf. on Artificial Neural Networks, Churchill College, UK, University of Cambridge, 1997, IEE Conference Publication, 1997, vol. 440, pp. 285–290.

    Google Scholar 

  4. Dolenko, S.A., Orlov, Yu.V., Persiantsev, I.G., and Shugai, Yu.S., Use of self-organization principles in construction of hierarchical neural network classifiers, Pat. Rec. Image Analysis, 1998, vol. 8, no. 2, pp. 122–124.

    Google Scholar 

  5. Orlov, Yu.V., Razrabotka I issledovanie algoritmov postroeniya neirosetevykh kompleksov dlya klassifikacii dannyh fizichskih izmereniy (Development and Study of Algorithms for Construction of Neural Network Complexes for Classification of Physical Measurements Data), SINP MSU, Candidate (PhD) Thesis in Physics and Mathematics, 2003 (in Russian).

    Google Scholar 

  6. Persiantsev, I.G., Adaptivnoe postroenie ierarhicheskih neirosetevykh sistem dlya classifikacii i dlya segmentacii vremennykh ryadov (Adaptive Construction of Hierarchical Neural Network Systems for Classification and for Segmentation of Time Series), in XII All-Russian scientific and Technical Conference “Neuroinformatics-2010”: Lectures in Neuroinformatics, Moscow, NRNU MEPhI, 2010, pp. 212–242 (in Russian).

    Google Scholar 

  7. Tao Li, Tang Yuan, Y., and Fang, L.Y., A structure-parameter-adaptive (SPA) neural tree for the recognition of large character set, Pat. Rec., 1995, vol. 28, no. 3, pp. 315–329.

    Article  Google Scholar 

  8. Song, H.H. and Lee, S.W., A self-organizing neural tree for large-set pattern classification, IEEE Trans. Neural Networks, 1998, vol. 9, no. 3, pp. 369–380, DOI: 10.1109/72.668880.

    Article  Google Scholar 

  9. Micheloni, C., Rani, A., Kumar, S., and Foresti, G.L., A balanced neural tree for pattern classification, Neural Networks, 2012, vol. 27, pp. 81–90, DOI: 10.1016/j.neunet.2011.10.007.

    Article  Google Scholar 

  10. Kryzhanovsky V., Malsagov M., and Tomas J.A.C., Hierarchical classifier: based on neural networks searching tree with iterative traversal and stop criterion, Opt. Mem. Neural Networks, Ser. Inform. Opt., 2013, vol. 22, no. 4, pp. 2170–223, DOI: 10.3103/S1060992X13040012.

    Google Scholar 

  11. Foresti, G.L. and Micheloni, C., Generalized neural trees for pattern classification, IEEE Trans. Neural Networks, 2002, vol. 13, no. 6, pp. 1540–1547, DOI: 10.1109/TNN.2002.804290.

    Article  Google Scholar 

  12. C++ 11, http://www.open-std.org/jtc1/sc22/wg21/.

  13. FANN C library, http://leenissen.dk/fann/wp/.

  14. “Textures” problem, ELENA: Enhanced Learning for Evolutive Neural Architecture, ESPRIT Basic Research Project Number 6891, https://www.elen.ucl.ac.be/neural-nets/Research/Projects/ELENA/elena.htm.

  15. “Vowels” problem, Lichman, M., 2013, UCI Machine Learning Repository, Irvine, CA: University of California, School of Information and Computer Science, https://archive.ics.uci.edu/ml/datasets/Connectionist+Bench+%28Vowel+Recognition+-+Deterding+Data%29.

Download references

Author information

Authors and Affiliations

  1. D.V. Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University, Moscow, Russia

    V. A. Svetlov, I. G. Persiantsev, J. S. Shugay & S. A. Dolenko

  2. Physical Department, M.V. Lomonosov Moscow State University, Moscow, Russia

    V. A. Svetlov

Authors
  1. V. A. Svetlov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. I. G. Persiantsev
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. S. Shugay
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. S. A. Dolenko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. A. Svetlov.

Additional information

This study has been supported by a grant of the Russian Foundation for Basic Research, project no. 15-07-08975.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Svetlov, V.A., Persiantsev, I.G., Shugay, J.S. et al. A new implementation of the algorithm of adaptive construction of hierarchical neural network classifiers. Opt. Mem. Neural Networks 24, 288–294 (2015). https://doi.org/10.3103/S1060992X15040062

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S1060992X15040062

Keywords

Search

Navigation