COMPARATIVE CHARACTERISTICS OF KERAS AND LASAGNE MACHINE LEARNING PACKAGES

Authors

  • V. M. Sineglazov National Aviation University, Kyiv
  • M. O. Omelchenko National Aviation University, Kyiv
  • V. P. Hotsyanivskyy National Aviation University, Kyiv

DOI:

https://doi.org/10.18372/1990-5548.53.12151

Keywords:

Automation deep learning, image processing, convolutional neural networks.

Abstract

A comparative analysis of the Lasagne and Keras computer libraries has been performed to construct convolutional neural networks used in image processing systems. The carried out researches have allowed to define their advantages and disadvantages that will allow to make to researchers the correct choice at the decision of applied problems.

Author Biographies

V. M. Sineglazov, National Aviation University, Kyiv

Educational & Research Institute of Information and Diagnostic Systems

Doctor of Engineering Science. Professor

M. O. Omelchenko, National Aviation University, Kyiv

Educational & Research Institute of Information and Diagnostic Systems

Student

V. P. Hotsyanivskyy, National Aviation University, Kyiv

Educational & Research Institute of Information and Diagnostic Systems

Student

References

A. N. Gordan, D. A. Rossiev, S. E. Gilev, et al. “NeuroComp” group: neural-networks software and its application. Russian Academy of Sciences, Krasnoyarsk Computing Center. Preprint no. 8. Krasnoyarsk, 1995. (in Russian)

T. Lisman and R. J. Porte. Towards a rational use of low-molecular-weight heparin in patients with cirrhosis. Liver Int., London: Science of Medicine 2011.

M. Riesenhuber. Object recognition in cortex: Neural mechanisms, and possible roles for attention Department of Neuroscience Georgetown University Medical Center, Washington, DC, 2007.

Downloads

Issue

Section

MATHEMATICAL MODELING OF PROCESSES AND SYSTEMS