ISSN 1991-2927
 

ACP № 3 (61) 2020

Author: "Sergei Vladimirovich Sukhov"

/table>

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.

Aleksandr Viacheslavovich Mikheev, Ulyanovsk Regional Center of New Information Technologies of Ulyanovsk State Technical University, graduated from Ulyanovsk State Technical University; Software Engineer at the Ulyanovsk Regional Center of New Information Technologies of Ulyanovsk State Technical University; his research interests include machine learning. [e-mail: a.miheev@simcase.ru]A. Mikheev,

Kirill Valerevich Sviatov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies at UlSTU; an author of 40 articles, 3 monographs, 1 textbook, and 4 State Registration Certificate of the Computer Program; his research interests are in the field of machine learning and robotics. [e-mail: k.svyatov@ulstu.ru]K. Sviatov,

Daniil Pavlovich Kanin, Ulyanovsk State Technical University, a student of the Faculty of Information Systems and Technologies of the Computer Science Department at Ulyanovsk State Technical University, a winner of robotics competitions; his research interests are in the field of machine learning. [e-mail: dan-kan@mail.ru]D. Kanin,

Sergei Vladimirovich Sukhov, Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Candidate at Science in Physics and Mathematics; graduated from the Ulyanovsk Branch of Lomonosov Moscow State University; Senior Researcher at the Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences; an author of one monograph, 70 articles, and 2 patents for inventions; his research interests are in the field of optics, computational neurobiology, machine learning [e-mail: ssukhov@knights.ucf.edu]S. Sukhov,

Vadim Georgievich Tronin, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Associated Professor at the Department of Information Systems of UlSTU; an author of 50 articles, 1 textbook; his research interests are in the field of project management and theory of inventive problem-solving. [e-mail: v.tronin@ulstu.ru]V. Tronin

The Scene Segmentation in the Tasks for Self-driving Vehicle Navigation By Using Neural Network Models With Attention 55_5.pdf

The article deals with the designing process of software module for the road signs recognition. This module is designated for the use in the automated control system of self-driving vehicles and is being developed at Ulyanovsk State Technical University.The creation of the training dataset sufficient to train neural network models is one of the major tasks to be solved when creating computer vision systems for self-driving vehicles. In this case, the preparation of a large sample in the semantic scene segmentation task may require considerable efforts for “manual” labeling. Authors describe a convolutional network model with a soft attention mechanism. This network is trained in the classification task with the possibility of extracting an attention mask from the internal network state, which can be used for the semantic image segmentation. This approach allows to reduce data-labeling costs significantly.

Artificial intelligence, neural networks, machine learning, computer vision, attention networks.

2019_ 1

Sections: Information systems

Subjects: Information systems, Artificial intelligence.



Aleksandr Viacheslavovich Mikheev, Ulyanovsk State Technical University, graduated from Ulyanovsk State Technical University; Software Engineer of Ulyanovsk Regional Center for New Information Technologies at Ulyanovsk State Technical University; his research interests include machine learning. [e-mail: a.miheev@simcase.ru]A. Mikheev,

Kirill Valerevich Sviatov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University;an author of 40 articles, three monographs, one textbook, and four certificates of registration of computer software programs; his research interests include machine learning and robotics. [e-mail: k.svyatov@ulstu.ru]K. Sviatov,

Sergei Vladimirovich Sukhov, Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Candidate of Science 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 Radioengineering and Electronics of the Russian Academy of Sciences; an author of one monograph, 70 articles, two patents of inventions in the field of optics, computational neurobiology, machine learning. [e-mail: ssukhov@knights.ucf.edu]S. Sukhov,

Daniil Pavlovich Kanin, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: dan-kan@mail.ru]D. Kanin,

Iakov Andreevich Akimov, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: yasha.akimov.73@gmail.com]I. Akimov,

Pavel Mikhailovich Volkov, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: p.vollkkoff@yandex.ru]P. Volkov

Changing the Lighting in the Scenes By Using Neural Networks Cascades 54_7.pdf

The article describes the process of creating the artificial illumination of surfaces taking into account shadows on convex and concave surfaces using machine learning algorithms and methods of working with three-dimensional objects.Despite the variety of applications for photo processing (LightRoom, Photoshop, Snapchat, Instagram etc.), there is a problem associated with the correct modeling of lighting on surfaces, due to the peculiarity of the photo format. First, the photo is a two-dimensional object and contains only indirect information about three-dimensional objects depicted on it. Secondly, the photoimage captures a certain state of objects with a certain set of properties, which are not enough for modeling shadows and lighting. The missing information is difficult to recreate by classical algorithms or heuristics because of the large number of parameters for recognition of objects in the photo and their possible combinations. However, machine learning algorithms are able to approximate very complex functional relationships based on training samples. This article describes the solution to the problem of modeling artificial lighting and shadows in photography using several neural networks trained on synthetic data.

Artificial intelligence, neural networks, machine learning, computer vision.

2018_ 4

Sections: Artificial intelligence

Subjects: Artificial intelligence.


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