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

Vol. 3 No. 53 (2017)

Section

MATHEMATICAL MODELING OF PROCESSES AND SYSTEMS

License

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 (See The Effect of Open Access).