Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Sergey Mosin"'
Publikováno v:
Procedia Computer Science. 171:1927-1934
The application of a combination of convolutional neural networks for the recognition of handwritten digits is considered. Recognition is carried out by two sets of the networks following each other. The first neural network selects two digits with m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e8decfa09dca9bce03df7e90927a5f7
https://doi.org/10.1016/j.procs.2020.04.206
https://doi.org/10.1016/j.procs.2020.04.206
Autor:
Sergey Mosin
Publikováno v:
Lecture Notes in Computational Science and Engineering ISBN: 9783030878085
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7dda16b28ac65d18b9450cd8730c93de
https://doi.org/10.1007/978-3-030-87809-2_26
https://doi.org/10.1007/978-3-030-87809-2_26
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9783030847593
The influence of binarization on the recognition of handwritten digits has been investigated. The main methods of converting images from grayscale to black and white images are analyzed. The binarization process is applied to images of handwritten di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b874d38b270955883d0bd376b6762ed
https://doi.org/10.1007/978-3-030-84760-9_9
https://doi.org/10.1007/978-3-030-84760-9_9
Autor:
Sergey Mosin, Maxim Kislyakov
Publikováno v:
EWDTS
Microelectronics is one of the drivers of the world economy. The global pandemic (Covid-19) has negatively influenced on mostly all industries and sectors of the world economy, including microelectronics. Some results of such influence on microelectr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2240663b8bd1990749924c3240238ac
https://doi.org/10.1109/ewdts52692.2021.9581014
https://doi.org/10.1109/ewdts52692.2021.9581014
Autor:
Sergey Mosin
Publikováno v:
Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitel'naya tekhnika i informatika. :103-111
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5844334ed348043dc206c4b20a33f276
https://doi.org/10.17223/19988605/48/12
https://doi.org/10.17223/19988605/48/12
Autor:
Sergey Mosin
Publikováno v:
Russian Microelectronics. 48:310-317
Methods of machine learning are actively used to construct neuromorphic fault dictionaries that provide the fault diagnostics of analog and mixed-signal integrated circuits in an associative mode. Many problems of the neural network (NN) training ass
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d81d9208a4af7710ffcc4dc646d4a59
https://doi.org/10.1134/s1063739719050081
https://doi.org/10.1134/s1063739719050081
Publikováno v:
Electronics; Volume 11; Issue 15; Pages: 2335
The development of digital technologies is in many ways associated with an improvement of integrated technologies, microelectronic components, and the capabilities of hardware acceleration of the most computationally complex operations. Field-program
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23b2fb6d41b1283dff5d0c3c12a75cf5
https://doi.org/10.3390/electronics11152335
https://doi.org/10.3390/electronics11152335
Publikováno v:
2021 23rd International Conference on Digital Signal Processing and its Applications (DSPA).
Recognition of handwritten digits by convolutional neural network (CNN) using Fourier transforms of images as a preprocessing is considered. An algorithm of image preprocessing for effective CNN training and handwritten digits recognition is proposed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d009328bd539d4627a90ddd8d888e1f
https://doi.org/10.1109/dspa51283.2021.9535947
https://doi.org/10.1109/dspa51283.2021.9535947
An Accuracy Improvement of the Neuromorphic Functional Models by Using the Parallel ANN Architecture
Autor:
Sergey Mosin
Publikováno v:
EWDTS
Enhancement of the up-to-date computing systems in performance and memory capacity stimulates development of new mathematical models and methods for numerical simulation. Machine learning methods are widely used nowadays in the electronic design auto
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca7861c337c1d6b11ec18448dd389896
https://doi.org/10.1109/ewdts50664.2020.9225034
https://doi.org/10.1109/ewdts50664.2020.9225034
Autor:
Roman Kirichenko, Salavat Khasanov, Sergey Mosin, Dmitriy Vasilyuc, Dmitriy Ievlev, Olga Levitova
Publikováno v:
Perm National Research Polytechnic University Aerospace Engineering Bulletin. :82-94
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9b23d0a8ec937ca2ccbfda7d0ae3911
https://doi.org/10.15593/2224-9982/2017.51.08
https://doi.org/10.15593/2224-9982/2017.51.08