Hierarchical Convolutional Neural Network for Handwritten Digits Recognition

dc.contributor.author	Kayumov Z.
dc.contributor.author	Tumakov D.
dc.contributor.author	Mosin S.
dc.date.accessioned	2021-02-25T06:54:22Z
dc.date.available	2021-02-25T06:54:22Z
dc.date.issued	2020
dc.identifier.uri	https://dspace.kpfu.ru/xmlui/handle/net/161426
dc.description.abstract	© 2020 The Authors. Published by Elsevier B.V. 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.
dc.subject	Handwritten digitss
dc.subject	Hierarchical convolutional neural network
dc.subject	MNIST
dc.subject	recognition
dc.title	Hierarchical Convolutional Neural Network for Handwritten Digits Recognition
dc.type	Conference Paper
dc.relation.ispartofseries-volume	171
dc.collection	Публикации сотрудников КФУ
dc.relation.startpage	1927
dc.source.id	SCOPUS-2020-171-SID85086633513

Файлы в этом документе

Размер: 329.0Kb

Формат: PDF

Публикации сотрудников КФУ Scopus [24551]
Коллекция содержит публикации сотрудников Казанского федерального (до 2010 года Казанского государственного) университета, проиндексированные в БД Scopus, начиная с 1970г.