| Peer-Reviewed

Improving of Procedures for Preparing of Training Set for Neural Networks

Received: 14 June 2015     Accepted: 28 July 2015     Published: 1 August 2015
Views:       Downloads:
Abstract

In the article procedure of rough-down of information is examined for teaching of neuron networks. Shown, that exists problem of normalization of ordinals of variables in part of their internal levels. The improved chart of normalization, allowing setting ponder ability both ordinal of variable on the whole and its separate levels, is offered to application. Reverse normalization formulas over are also brought for interpretation of gravimetric coefficients of neurons

Published in American Journal of Neural Networks and Applications (Volume 1, Issue 1)
DOI 10.11648/j.ajnna.20150101.14
Page(s) 29-32
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2015. Published by Science Publishing Group

Keywords

Neuron, Normalization, Ordinal Variable, Neural Network, Self-Organizing Maps

References
[1] Mirkes E. M. Nejrokomp'yuter: proekt standarta / E. M. Mirkes; red. V. L. Dunin-Barkovskij; RAN, SO, In-t vychisl. modelirovaniya. – M.: Nauka: Sib. predpriyatie RAN, 1999. – 190 s.
[2] Zaencev I. V. Nejronnye seti: osnovnye modeli. – Voronezh: VGU, 1999. – 157 s.
[3] Gorban' A. N. Nejroinformatika / A. N. Gorban', V. L. Dunin-Barkovskij, A. N. Kirdin. – Novosibirsk: Nauka. Sibirskoepredpriyatie RAN. – 1998. – 296 s.
[4] [4] Caregorodcev V. G. Optimizaciya predobrabotki dannyh: konstanta Lipshica obuchayushchej vyborki i svojstva obuchennyh nejronnyh setej // Nejrokomp'yutery: razrabotka i primenenie.–2003.–№ 7.–S. 3-8.
[5] [5] Gitis T. P. Analiz urovnya professional'nogo razvitiya stanochnikov s ispol'zovaniem kart Kohonena / T. P. Gitis // Sbornik trudov Mezhdunarodnoj nauchnoj konferencii «Nejrosetevye tekhnologii i ih primenenie». – Kramatorsk: DGMA. – 2012. – S. 34-38.
[6] Es'kov A. L. Upravlenie professional'nym razvitiem personala predpriyatiya na osnove ego ocenki / A. L. Es'kov, T. P. Gitis // Ekonomіka ta pravo. – 2013. - №2(36). – S.87-92
[7] Gitis T. P. Intellektual'nye metody upravleniya personalom predpriyatiya: monografiya / T. P. Gitis, V. B. Gitis. - Kramatorsk, DGMA, 2014. – 140 s.
[8] Gitis T. P. Predvaritel'naya obrabotka dannyh dlya ocenki urovnya professional'nogo razvitiya rabochih s pomoshch'yu kart Kohonena / T. P. Gitis // Iskusstvennyj intellekt. Intellektual'nye sistemy: Materialy X mezhdunarodnoj nauchno-tekhnicheskoj konferencii. – Taganrog: Izd-vo TTI YUFU, 2009. – S. 74-76
[9] Gitis T. P. Pred- i postobrabotka informacionnyh potokov samoorganizuyushchihsya kart priznakov / T. P. Gitis, V. B. Gitis // Materialy Mezhdunarodnoj nauchno-tekhnicheskoj konferencii «Iskusstvennyj intellekt. Intellektual'nye sistemy II-2013». −Doneck: IPII «Naukaіosvіta», 2013. – S. 265-267.
[10] Gitis T. P. Sovershenstvovanie procedury podgotovki obuchayushchih mnozhestv dlya nejronnyh setej / T. P. Gitis, V. B. Gitis // Vіsnik Donbas'koї derzhavnoї mashinobudіvnoї akademії. – 2011. – № 2 (8E). – S. 42-46.
Cite This Article
  • APA Style

    Veniamin B. Gitis, Tatyana P. Gitis. (2015). Improving of Procedures for Preparing of Training Set for Neural Networks. American Journal of Neural Networks and Applications, 1(1), 29-32. https://doi.org/10.11648/j.ajnna.20150101.14

    Copy | Download

    ACS Style

    Veniamin B. Gitis; Tatyana P. Gitis. Improving of Procedures for Preparing of Training Set for Neural Networks. Am. J. Neural Netw. Appl. 2015, 1(1), 29-32. doi: 10.11648/j.ajnna.20150101.14

    Copy | Download

    AMA Style

    Veniamin B. Gitis, Tatyana P. Gitis. Improving of Procedures for Preparing of Training Set for Neural Networks. Am J Neural Netw Appl. 2015;1(1):29-32. doi: 10.11648/j.ajnna.20150101.14

    Copy | Download

  • @article{10.11648/j.ajnna.20150101.14,
      author = {Veniamin B. Gitis and Tatyana P. Gitis},
      title = {Improving of Procedures for Preparing of Training Set for Neural Networks},
      journal = {American Journal of Neural Networks and Applications},
      volume = {1},
      number = {1},
      pages = {29-32},
      doi = {10.11648/j.ajnna.20150101.14},
      url = {https://doi.org/10.11648/j.ajnna.20150101.14},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20150101.14},
      abstract = {In the article procedure of rough-down of information is examined for teaching of neuron networks. Shown, that exists problem of normalization of ordinals of variables in part of their internal levels. The improved chart of normalization, allowing setting ponder ability both ordinal of variable on the whole and its separate levels, is offered to application. Reverse normalization formulas over are also brought for interpretation of gravimetric coefficients of neurons},
     year = {2015}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Improving of Procedures for Preparing of Training Set for Neural Networks
    AU  - Veniamin B. Gitis
    AU  - Tatyana P. Gitis
    Y1  - 2015/08/01
    PY  - 2015
    N1  - https://doi.org/10.11648/j.ajnna.20150101.14
    DO  - 10.11648/j.ajnna.20150101.14
    T2  - American Journal of Neural Networks and Applications
    JF  - American Journal of Neural Networks and Applications
    JO  - American Journal of Neural Networks and Applications
    SP  - 29
    EP  - 32
    PB  - Science Publishing Group
    SN  - 2469-7419
    UR  - https://doi.org/10.11648/j.ajnna.20150101.14
    AB  - In the article procedure of rough-down of information is examined for teaching of neuron networks. Shown, that exists problem of normalization of ordinals of variables in part of their internal levels. The improved chart of normalization, allowing setting ponder ability both ordinal of variable on the whole and its separate levels, is offered to application. Reverse normalization formulas over are also brought for interpretation of gravimetric coefficients of neurons
    VL  - 1
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Intelligent Decision Support Systems Department, Faculty of Machine Automation and Information Technology, Donbass State Engineering Academy, Kramatorsk, Ukraine

  • Intelligent Decision Support Systems Department, Faculty of Machine Automation and Information Technology, Donbass State Engineering Academy, Kramatorsk, Ukraine

  • Sections