SOME METHODS OF ADAPTIVE MULTILAYER NEURAL NETWORKS TRAINING

Authors

  • Leonid Makhnist
  • Nikolaj Maniakov
  • Nikolaj Maniakov

DOI:

https://doi.org/10.47839/ijc.3.1.259

Keywords:

Multilayer Neural Networks, Gradient Descent Method, Adaptive Training Step

Abstract

Is proposed two new techniques for multilayer neural networks training. Its basic concept is based on the gradient descent method. For every methodic are showed formulas for calculation of the adaptive training steps. Presented matrix algorithmizations for all of these techniques are very helpful in its program realization.

References

N. Maniakov, L. Makhnist. Matrix algorithmization of multilayer neural networks’ training process with use of gradient descents methods, Vestnik BGTU 5 (17) (2002). p. 60-64.

V. Golovko, N. Maniakov, L. Makhnist. Multilayer Neural Networks Training Methodic. Proceedings of the Second IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS’2003), Lviv, Ukraine, 8-10 September 2003, pp. 185-190.

Downloads

Published

2014-08-01

How to Cite

Makhnist, L., Maniakov, N., & Maniakov, N. (2014). SOME METHODS OF ADAPTIVE MULTILAYER NEURAL NETWORKS TRAINING. International Journal of Computing, 3(1), 99-106. https://doi.org/10.47839/ijc.3.1.259

Issue

2004, Volume 3, 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.