KFU. Card publication. Hierarchical Convolutional Neural Network for Handwritten Digits Recognition

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

HIERARCHICAL CONVOLUTIONAL NEURAL NETWORK FOR HANDWRITTEN DIGITS RECOGNITION

Form of presentation

Articles in international journals and collections

Year of publication

2020

Язык

английский

Authors, employees of KFU

Kayumov Zufar Damirovich, author

Mosin Sergey Gennadevich, author

Tumakov Dmitriy Nikolaevich, author

Authors, students KFU

Kayumov Zufar Damirovich, author

Bibliographic description in the original language

Kayumov Z, Tumakov D, Mosin S., Hierarchical Convolutional Neural Network for Handwritten Digits Recognition//Procedia Computer Science. - 2020. - Vol.171, Is.. - P.1927-1934.

Annotation

The application of a combination of convolutional neural networks for the recognition of handwritten digits is considered. Recognition is carried out by two sets of the networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the next network is activated, which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The minimal handwriting recognition error was estimated with this approach.

Keywords

Handwritten digits; recognition; Hierarchical convolutional neural network; MNIST

The name of the journal

Procedia Computer Science

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086633513&doi=10.1016%2fj.procs.2020.04.206&partnerID=40&md5=9253c2b4e454acd44d8a54426cf8bf70

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=235382&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Kayumov Zufar Damirovich	ru_RU
dc.contributor.author	Mosin Sergey Gennadevich	ru_RU
dc.contributor.author	Tumakov Dmitriy Nikolaevich	ru_RU
dc.contributor.author	Kayumov Zufar Damirovich	ru_RU
dc.date.accessioned	2020-01-01T00:00:00Z	ru_RU
dc.date.available	2020-01-01T00:00:00Z	ru_RU
dc.date.issued	2020	ru_RU
dc.identifier.citation	Kayumov Z, Tumakov D, Mosin S., Hierarchical Convolutional Neural Network for Handwritten Digits Recognition//Procedia Computer Science. - 2020. - Vol.171, Is.. - P.1927-1934.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=235382&p_lang=2	ru_RU
dc.description.abstract	Procedia Computer Science	ru_RU
dc.description.abstract	The application of a combination of convolutional neural networks for the recognition of handwritten digits is considered. Recognition is carried out by two sets of the networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the next network is activated, which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The minimal handwriting recognition error was estimated with this approach.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject		ru_RU
dc.title	Hierarchical Convolutional Neural Network for Handwritten Digits Recognition	ru_RU
dc.type	Articles in international journals and collections	ru_RU