Skip to main content
SpringerLink
Log in

Multilevel neural net adaptive models using the metagraph approach

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

Abstract

The paper considers adaptive models enabling real-time processing of data flows. The drawbacks of current algorithms are examined. A method that combines advantages of deep learning, self-organizing neural nets and the metagraph approach is offered for designing adaptive models. A part of the method is realized, data clustering experiments are carried out and experimental results are analyzed.

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. Firebaugh, L. and Morris, W., Artificial Intelligence: A Knowledge-based Approach. Danvers, MA, USA: Fraser Publishing Co., 1988.

    Google Scholar 

  2. Bengio, Y., Courville, A., and Vincent, P., Representation Learning: A Review and New Perspectives, U. Montreal, USA: Department of Computer Science and operations research, 2014. doi 10.1109/TPAMI.2013.50

    Google Scholar 

  3. Xiao, X., Zhang, H., and Hasegawa, O., Density estimation method based on self-organizing incremental neural network and error estimation, Proceedings of the Neural Information Processing: 20th International Conference, ICONIP 2013, Daegu, Korea, 2013, pp. 43–50. doi 10.1007/978-3-642-42042-9_610.1007/978-3-642-42042-9_6

    Chapter  Google Scholar 

  4. Samokhvalov, E.N., Revunkov, G.I., and Gapanyuk, Yu.E., Using Metagraphs to Describe Semantics and Pragmatics of Information Systems, Bauman State Technical University Bulletin, “Instrumentation” Series, 2015, Issue 1.

    Google Scholar 

  5. Hornik, K., Stinchcombe M., and White, H., Multilayer feedforward networks are universal approximators, Neural Networks, 1989, vol. 2, pp. 359–366. doi 10.1016/0893-6080(89)90020-8

    Article  Google Scholar 

  6. Leshno, M., Lin, V.Y., Pinkus, A., and Schocken, S., Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural Networks, 1993, vol. 6, pp. 861–867. doi 10.1016/S0893-6080(05)80131-5

    Article  Google Scholar 

  7. Hinton, G.E., Osindero, S., and Teh, Y., A fast learning algorithm for deep belief nets, Neural Computation, Vol. 7, USA, MA, Cambridge: MIT Press, 2006, pp. 1527–1554. doi 10.1162/neco.2006.18.7.1527

    MATH  Google Scholar 

  8. Bengio, Y. and Lecun, Y., Scaling learning algorithms towards AI, Large-Scale Kernel Machines, Vol. 5, USA, MA, Cambridge: MIT Press, 2007, pp. 127–168.

    Google Scholar 

  9. Furao S. and Hasegawa, O., An incremental network for on-line unsupervised classification and topology learning, Neural Networks, 2005, no. 4, pp. 1–17. doi 10.1016/j.neunet.2005.04.006

    MATH  Google Scholar 

  10. Stijn Van Dongen, Graph clustering via a discrete uncoupling process, Siam J. Matrix Analysis Appl. (SIAM), vol. 30, p. 1; Philadelphia, USA: Society for Industrial and Applied Mathematics, 2008, pp. 121–141. doi 10.1137/040608635

    Google Scholar 

  11. Manning, C.D., Raghavan, P., and Schutze, H., Introduction to Information Retrieval, Cambridge University Press, 2010, p. 521.

    MATH  Google Scholar 

  12. Rosenblatt, F., Principles of Neurodynamics, Mir Publishing, 1965.

    MATH  Google Scholar 

  13. Minsky, M. and Papert, S., Perceptrons, Mir Publishing, 1971.

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. N.E. Bauman Moscow State Technical University, Moscow, Russia

    Yuri S. Fedorenko & Yuri E. Gapanyuk

Authors
  1. Yuri S. Fedorenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuri E. Gapanyuk
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuri S. Fedorenko.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fedorenko, Y.S., Gapanyuk, Y.E. Multilevel neural net adaptive models using the metagraph approach. Opt. Mem. Neural Networks 25, 228–235 (2016). https://doi.org/10.3103/S1060992X16040020

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S1060992X16040020

Keywords

Search

Navigation