Zobrazeno 1 - 10
of 447
pro vyhledávání: '"Sboev, A."'
Spiking Neural Networks have attracted significant attention in recent years due to their distinctive low-power characteristics. Meanwhile, Transformer models, known for their powerful self-attention mechanisms and parallel processing capabilities, h
Externí odkaz:
http://arxiv.org/abs/2412.13553
Autor:
Sboev, Alexander G., Kudryshov, Nikolay A., Moloshnikov, Ivan A., Zavertyaev, Saveliy V., Naumov, Aleksandr V., Rybka, Roman B.
Currently, the evolution of Covid-19 allows researchers to gather the datasets accumulated over 2 years and to use them in predictive analysis. In turn, this makes it possible to assess the efficiency potential of more complex predictive models, incl
Externí odkaz:
http://arxiv.org/abs/2207.07689
Autor:
Moloshnikov, Ivan A. a, b, Sboev, Alexander G. a, b, ⁎, Kutukov, Aleksandr A. b, Rybka, Roman B. a, b, Kuvakin, Mikhail S. a, Fedorov, Oleg O. a, c, Zavertyaev, Saveliy V. b
Publikováno v:
In Chaos, Solitons and Fractals: the interdisciplinary journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena March 2025 192
Autor:
Rybka, Roman Борисович, Vlasov, Danila Sergeevich, Manzhurov, Alexander Igorevich, Serenko, Alexey Вячеславович, Sboev, Alexander Georgievich
Publikováno v:
Известия высших учебных заведений: Прикладная нелинейная динамика, Vol 32, Iss 2, Pp 239-252 (2024)
Purpose. Studying the possibility of implementing a data classification method based on a spiking neural network, which has a low number of connections and is trained based on local plasticity rules, such as Spike-Timing-Dependent Plasticity. Methods
Externí odkaz:
https://doaj.org/article/a2353d55348640e0a9f6b71174e56e63
Publikováno v:
In Expert Systems With Applications 1 July 2024 245
Autor:
Sboev, Alexander, Sboeva, Sanna, Moloshnikov, Ivan, Gryaznov, Artem, Rybka, Roman, Naumov, Alexander, Selivanov, Anton, Rylkov, Gleb, Ilyin, Viacheslav
We present the full-size Russian complexly NER-labeled corpus of Internet user reviews, along with an evaluation of accuracy levels reached on this corpus by a set of advanced deep learning neural networks to extract the pharmacologically meaningful
Externí odkaz:
http://arxiv.org/abs/2105.00059
Autor:
Vlasov, Danila, Minnekhanov, Anton, Rybka, Roman, Davydov, Yury, Sboev, Alexander, Serenko, Alexey, Ilyasov, Alexander, Demin, Vyacheslav
Publikováno v:
In Neural Networks September 2023 166:512-523
Publikováno v:
Big Data and Cognitive Computing, Vol 8, Iss 3, p 22 (2024)
Developing a spiking neural network architecture that could prospectively be trained on energy-efficient neuromorphic hardware to solve various data analysis tasks requires satisfying the limitations of prospective analog or digital hardware, i.e., l
Externí odkaz:
https://doaj.org/article/fd3048681e994502b23db8a177c6e899
Autor:
Sboev, D. A.1 (AUTHOR) dnlsboev@gmail.com
Publikováno v:
Siberian Mathematical Journal. Nov2023, Vol. 64 Issue 6, p1420-1438. 19p.
Autor:
Alexander Sboev, Roman Rybka, Dmitry Kunitsyn, Alexey Serenko, Vyacheslav Ilyin, Vadim Putrolaynen
Publikováno v:
Big Data and Cognitive Computing, Vol 7, Iss 4, p 184 (2023)
In this paper, we demonstrate that fixed-weight layers generated from random distribution or logistic functions can effectively extract significant features from input data, resulting in high accuracy on a variety of tasks, including Fisher’s Iris,
Externí odkaz:
https://doaj.org/article/bc35e65818554e7fbad1f7747e10fdca