Convolution Neural Network Learning Features for Handwritten Digit Recognition

dc.contributor.author	Kayumov Z.
dc.contributor.author	Tumakov D.
dc.date.accessioned	2021-02-25T06:54:58Z
dc.date.available	2021-02-25T06:54:58Z
dc.date.issued	2020
dc.identifier.uri	https://dspace.kpfu.ru/xmlui/handle/net/161495
dc.description.abstract	© 2020 IEEE. The classical six-layer neural network is considered. This network is used to recognize handwritten digit patterns from the MNIST database. The influence of the size of mini-batches on the learning speed and pattern recognition accuracy is analyzed. The optimal sizes of mini-batch are obtained. The relationship between the accuracy of training and the accuracy of test samples is considered. The change in the values of the radius vector of the scales during training is shown. Conclusions are drawn about the influence of the initial value of the balance on the recognition accuracy. A more accurate formula is obtained for the limits, in which the initial values of the weights of the neural network are generated.
dc.subject	convolutional neural network
dc.subject	handwritten digits
dc.subject	neural network training
dc.subject	recognition
dc.title	Convolution Neural Network Learning Features for Handwritten Digit Recognition
dc.type	Conference Paper
dc.collection	Публикации сотрудников КФУ
dc.source.id	SCOPUS-2020-SID85096425861

Файлы в этом документе

Имя: SCOPUS-2020-SID85 ...

Размер: 50.09Kb

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.