Compressing a convolution neural network based on quantization

Issue Date Author Title Subject

Please use this identifier to cite or link to this item: https://elib.bsu.by/handle/123456789/306248

Full metadata record

DC Field	Value	Language
dc.contributor.author	Pertsau, Dmitry
dc.contributor.author	Lukashevich, Marina
dc.contributor.author	Kupryianava, Dziana
dc.date.accessioned	2023-12-12T12:42:17Z	-
dc.date.available	2023-12-12T12:42:17Z	-
dc.date.issued	2023
dc.identifier.citation	Pattern Recognition and Information Processing (PRIP’2023). Artificial Universe: New Horisont : Proceedings of the 16 th International Conference, Belarus, Minsk, October 17–19, 2023 / Belarusian State University : eds. A. Nedzved, A. Belotserkovsky. – Minsk : BSU, 2023. – Pp. 269-272.
dc.identifier.isbn	978-985-881-522-6
dc.identifier.uri	https://elib.bsu.by/handle/123456789/306248	-
dc.description.abstract	Modern deep neural network models contain a large number of parameters and have a significant size. In this paper we experimentally investigate approaches to compression of convolutional neural network. The results showing the efficiency of quantization of the model while maintaining high accuracy are obtained
dc.language.iso	en
dc.publisher	Minsk : BSU
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Кибернетика
dc.subject	ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика
dc.title	Compressing a convolution neural network based on quantization
dc.type	conference paper
Appears in Collections:	2023. Pattern Recognition and Information Processing (PRIP’2023). Artificial Intelliverse: Expanding Horizons

Files in This Item:

File	Description	Size	Format
269-272.pdf		440,46 kB	Adobe PDF	View/Open