APPLICATION OF THE GROUP METHOD OF DATA HANDLING IN SYNTHESIS OF SUPRVISED NEURAL NETWORKS

Authors

  • Andrew V. Homich
  • Leonid A. Zhukov

DOI:

https://doi.org/10.47839/ijc.5.1.380

Keywords:

Artificial neural network, Evolutionary algorithms, GMDH

Abstract

The expediency of application of group method of data handling (GMDH) in synthesis supervised artificial neural networks is considered. Comparison of efficiency of two variants GMDH is carried out. Methods using entrance variables on everyone and only the first line of selection are considered. Efficiency of offered methods is estimated experimentally on practical problems.

References

Inductive method of self-organizing of complex systems / Ivahnenko A.G.-Kiev: Sciences idea, 1981-296 p.

Method of evolutionary optimization and its application to a problem of synthesis of artificial neural networks / Homich A.V., Zhukov L.A. // Neurocomputers: designing, application. - 2004. - № 12. - pp. 3-15.

Gilev S.E. Training of neural networks: Methods, algorithms, test tests, examples of the application: the Dissertation of the candidate of physical and mathematical sciences. Krasnoyarsk, 1997. - 187 p.

Gorban A.N. Training of neural networks. M.: publishing house the USSR - USA of joint venture " ParaGraph ", 1990.-160 p.

Homich A.V., Zhukov L.A. Recurrent and multilayered neural networks optimization of topology with application of genetic algorithms // Neuroinformatic-2004. The collection of proceedings. P.2. M.: MEPhI, 2004. pp. 68-74.

Whitley D. Genetic Algorithms and Neural Networks, Genetic Algorithms in Engineering and Computer Science. pp: 203-216, 1995.

Hecht-Nielsen R. Neurocomputing. Addison Wesley Publ. Co., 1990, p.433

Farlow, S.J. (ed.), Self Organizing Methods in Modeling: GMDH Type Algorithms, (Marcel Dekker Inc., New York, 1984), p. 350.

Downloads

Published

2014-08-01

How to Cite

Homich, A. V., & Zhukov, L. A. (2014). APPLICATION OF THE GROUP METHOD OF DATA HANDLING IN SYNTHESIS OF SUPRVISED NEURAL NETWORKS. International Journal of Computing, 5(1), 42-50. https://doi.org/10.47839/ijc.5.1.380

Issue

2006, Volume 5, Issue 1

Section

Articles

License

International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:
•    Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
•    Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
•    Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.