ISSN 1991-2927

ACP № 3 (61) 2020

Author: "Victoriia Iurevna Islenteva"


Viacheslav Andreevich Sergeev, Doctor of Sciences in Engineering, Professor; graduatedfromthe Faculty of Physics of Gorky State University n.a. Lobahevsky; Director of the Ulyanovsk Branch of the Kotel’nikov Institute of Radio- Engineering and Electronics of the Russian Academy of Sciences; Head of the Department of Radioengineering, Opto- and Nanoelectronics of Ulyanovsk State Technical University (UlSTU); an author of monographs, papers, and inventions in the field of modeling and researching semiconductor devices and integrated circuits characteristics and measuring its thermal parameters. e-mail: sva@ulstu.ruV. A. Sergeev

Mikhail Iurevich Leontev, completed postgraduate studies at the Faculty of Mathematics, Information, and Aviation Technologies at Ulyanovsk State University; Junior Research Associate of the Scientific and Research Institute of Technology n.a. S.P. Kapitsa; Leading Engineer of the Ulyanovsk Branch of the Kotel’nikov Institute of Radio-Engineering and Electronics of RAS; an author of eight articles, a certificate of registration for computer program. The area of his research interests relates to learning and robotics. e-mail: ulstaer@gmail.comM. I. Leontev

Victoriia Iurevna Islenteva, a student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of two articles. The area of her research interests relates to machine learning. e-mail: viksaskin@yandex.ruV. I. Islenteva

Sergei Vladimirovich Sukhov, Candidate of Sciences in Physics and Mathematics; graduated from the Ulyanovsk Branch of Lomonosov Moscow State University; Senior Staff Scientist at the Ulyanovsk Branch of the Kotel’nikov Institute of Radio-Engineering and Electronics of RAS; Associate Professor at the Department of Applied Mathematics and Informatics of UlSTU; an author of a monograph, 90 articles, two patents for inventions in the field of optics, computational neuroscience, and machine learning. e-mail: ssukhov@ulireran.ruS. V. Sukhov

Evaluation of generative approaches to knowledge sharing in neural networks60_8.pdf

The ability to interact and share knowledge among artificial neural networks (ANNs) is critical for further development of the artificial intelligence. One of the methods of knowledge sharing among ANNs may rely on the generation of training data using auxiliary generative models, which have recently become widespread. To make such methods more efficient, it is necessary to further improve the quality of artificial training data developed by generative models. The article proposes and tests several methods of enhancing characteristics of one of the classes of generative models, viz. variational autoencoders (VAE). It was improved both the VAE training procedure and changes in the model architecture. The improving methods of the quality of generated training data have been analyzed in terms of the efficiency of knowledge sharing among ANNs. To test the process of knowledge sharing among ANNs, the public training data sets have been used.

Generative networks, variational autoencoders, neural networks, machine learning, image classification, knowledge sharing.

2020_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.

© FRPC JSC 'RPA 'Mars', 2009-2018 The web-site runs on Joomla!