Two-dimensional matrix neural networks as alternative to modern state-of-the art ann architectures

Публікація:
Two-dimensional matrix neural networks as alternative to modern state-of-the art ann architectures

dc.contributor.author	Албасова, А. І.
dc.date.accessioned	2023-04-17T18:26:50Z
dc.date.available	2023-04-17T18:26:50Z
dc.date.issued	2020
dc.description.abstract	This work is devoted to the study of some issues related to the use of traditional vector-based neural networks to process non-vectorial inputs such as matrices. As traditional ANNs assume vector inputs, non-vectorial information must be previously converted to vector form. This process causes some problems, e.g. lost of information and decrease in learning speed. The purpose of this work is to point out the limits of traditional ANNs in handling nonvectorial data and consider matrix neural networks, which takes matrices directly as inputs.
dc.identifier.citation	Албасова А. І. Two-dimensional matrix neural networks as alternative to modern state-of-the art ann architectures / А. І. Албасова // Радіоелектроніка та молодь у ХХІ столітті : матеріали 24 Міжнар. молодіж. форуму, 7–9 квіт. 2020 р. – Харків : ХНУРЕ, 2020. – Т. 6. – С. 7–8.
dc.identifier.uri	https://openarchive.nure.ua/handle/document/22662
dc.language.iso	uk
dc.publisher	ХНУРЕ
dc.title	Two-dimensional matrix neural networks as alternative to modern state-of-the art ann architectures
dc.type	Conference proceedings
dspace.entity.type	Publication