Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Valentina A. Baboshina"'
Publikováno v:
IEEE Access, Vol 12, Pp 168428-168444 (2024)
In this paper we propose the fractional gradient descent for increasing the training and work of modern neural networks. This optimizer searches the global minimum of the loss function considering the fractional gradient directions achieved by Rieman
Externí odkaz:
https://doaj.org/article/05b7260c316444f697d41e5b3825d325
Publikováno v:
2022 International Conference on Quality Management, Transport and Information Security, Information Technologies (IT&QM&IS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6bbabbd7f8f2ded8fd1df9f63f4a58d5
https://doi.org/10.1109/itqmis56172.2022.9976753
https://doi.org/10.1109/itqmis56172.2022.9976753
Autor:
Pavel A. Lyakhov, Alexander S. Voznesensky, Evgeniy D. Shalugin, Anzor R. Orazaev, Valentina A. Baboshina
Publikováno v:
2022 11th Mediterranean Conference on Embedded Computing (MECO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bff653b12b2ccad1795ff30f4299a710
https://doi.org/10.1109/meco55406.2022.9797149
https://doi.org/10.1109/meco55406.2022.9797149
Publikováno v:
2022 11th Mediterranean Conference on Embedded Computing (MECO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2aabe44d6a7ec6169a2048ac8b456bb
https://doi.org/10.1109/meco55406.2022.9797124
https://doi.org/10.1109/meco55406.2022.9797124