350 rub
Journal Electromagnetic Waves and Electronic Systems №10 for 2013 г.
Article in number:
The recurrent neural network with managed synapses for handwriting recognition of coherent text
Keywords: neural network recurrent neural network synapse native penscript
Authors:
I.K. Belova - Ph.D.(Phys.-Math.), Associate professor, Chair - Software, information technologies, and applied mathematics?, Kaluga branch of the Bauman MSTU
E. O. Deriugina - Ph.D.(Eng.), Associate professor, Chair - Computer systems, complexes, and networks?, Kaluga branch of the Bauman MSTU
Abstract:
The article provides scientific justification for neural network selection for native penscript converting into electronic equivalent. One of the problems the authors had to deal with was the problem of native penscript manipulation quality improvement. For solving this problem the authors suggest to use the recurrent neural network with controllable synapses.
Pages: 36-39
References

  1. Galushkin A. I. Teoriya neironnykh setei. Book 1 / Ed. A.I. Galushkin. Moscow: IPRZhR. 2002. (inRussian)
  2. Osovskii S. Neironnye seti dlya obrabotki informatsii. Moscow: Finansy i statistika. 2002. (inRussian)
  3. Haykin S. Neural networks: A comprehensive foundation. Prentice Hall, 1999.
  4. Makarov I. M., Lokhin V. M., Manko S. V., Romanov P. M. Iskusstvennyi intellekt I intellektualnye sistemy upravleniya. Moscow: Nauka. 2006. (inRussian)
  5. Aizerman M. A., Braverman E. M., Rozonoer L. I. Metod potentsialnykh funktsii v teorii obucheniya mashin. Moscow: Nauka. 2004. (inRussian)
  6. Gorban A., Rossiev D. Neironnye seti na personalnom komp-yutere. Novosibirsk: Nauka. 1996. P. 114-119. (inRussian)
  7. ZhuravlevYu. I. Obalgebraicheskompodkhodekresheniyuzadachraspoznavaniyailiklassifikatsii // Problemykibernetiki. Moscow: Nauka. 2005. Issue 33. P. 5-25. (inRussian)
  8. Potapov A. S. Raspoznavanie obrazov I mashinnoe vospriyatie. Saint-Petersburg: Politekhnika. 2007. (inRussian)
  9. Rastrigin L. A., Erenshtein R. Kh. Metod kollektivnogo raspoznavaniya. Moscow: Energoizdat. 2006. (inRussian)
  10. RudakovK.V. ObalgebraicheskoiteoriiuniversalnykhIlokalnykhogranicheniidlyazadachklassifikatsii // Raspoznavanie, klassifikatsiya, prognoz. Matematicheskie metody I ikh primenenie. Issue. 1. Moscow: Nauka. 2007. P. 176-200. (inRussian)
  11. Fu K. Strukturnye metody v raspoznavanii obrazov. Moscow: Mir. 2005. (inRussian)
  12. KorotkiiS. Neironnyeseti: algoritmobratnogorasprostraneniya // lii.newmail.ru/kor_nn2.htm/
  13. Korotkii S. Neironnye seti: obuchenie bez uchitelya // masters.donntu.edu.ua/2006/fvti/lasebnik/library/art13.htm/
  14. Zhang Q., Benveniste A. Wavelet networks // IEEE Trans. Neural Networks. 1992. V. 3. P. 889-898.
  15. Wassermen F. Neirokomp-yuternaya tekhnika: teoriya I praktika. Moscow: Mir. 1992. (inRussian)