Hoppa till innehåll

Increasing of convolutional neural network performance using residue number system

This paper considers the method of pattern recognition based on a convolutional neural network using Sobel filters. Parameters of the convolutional neural network blocks were chosen experimentally by software modeling in MATLAB. We presents the architecture of the convolutional neural network constr...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Chervyakov, N. I., Червяков, Н. И., Lyakhov, P. A., Ляхов, П. А., Valueva, M. V., Валуева, М. В.
Materialtyp: Статья
Språk:English
Publicerad: Institute of Electrical and Electronics Engineers Inc. 2018
Ämnen:
Länkar:https://www.scopus.com/record/display.uri?eid=2-s2.0-85040520452&origin=resultslist&sort=plf-f&src=s&nlo=1&nlr=20&nls=afprfnm-t&affilName=nort*+caucas*+fed*+univ*&sid=6e44c4739f67eaef119fa92298a82e4b&sot=afnl&sdt=sisr&sl=53&s=%28AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29%29&ref=%28Increasing+of+convolutional+neural+network+performance+using+residue+number%29&relpos=0&citeCnt=0&searchTerm=
https://dspace.ncfu.ru:443/handle/20.500.12258/528
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!