Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/54297
Title: Neural network software technology trainable on the random search and gradient descent principles
Authors: Matskevich, V. A.
Xi Zhou
Qing Bu
Keywords: материалы конференций;framework;neural network;training algorithms;random search algorithms;annealing method
Issue Date: 2023
Publisher: BSU
Citation: Matskevich, V. A. Neural network software technology trainable on the random search and gradient descent principles / V. A. Matskevich, Xi Zhou, Qing Bu // Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023) : Proceedings of the 16th International Conference, October 17–19, 2023, Minsk, Belarus / United Institute of Informatics Problems of the National Academy of Sciences of Belarus. – Minsk, 2023. – P. 64–67.
Abstract: The paper considers an applied problem related to the construction of efficient neural network technologies implemented in the traditional frameworks' standards. It is shown that the increase in efficiency is achieved due to the additional inclusion in the framework's structure of training algorithms based on the ideas of random search. Original implementations of such algorithms are proposed, with experimental confirmation of their effectiveness. It is shown that in this case not only the solutions' obtained quality increases, but it is also possible to extend the range of applied problems to be solved.
URI: https://libeldoc.bsuir.by/handle/123456789/54297
Appears in Collections:Pattern Recognition and Information Processing (PRIP'2023) = Распознавание образов и обработка информации (2023)

Files in This Item:
File Description SizeFormat 
Matskevich_Neural.pdf243.1 kBAdobe PDFView/Open
Show full item record Google Scholar

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.