Logo BSU

Please use this identifier to cite or link to this item: https://elib.bsu.by/handle/123456789/158552
Title: A Simple Shallow Convolutional Neural Network for Accurate Handwritten Digit Classification
Authors: Golovko, V.
Mikhno, E.
Brichk, A.
Keywords: ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика
ЭБ БГУ::ОБЩЕСТВЕННЫЕ НАУКИ::Информатика
ЭБ БГУ::ТЕХНИЧЕСКИЕ И ПРИКЛАДНЫЕ НАУКИ. ОТРАСЛИ ЭКОНОМИКИ::Медицина и здравоохранение
Issue Date: 3-Oct-2016
Publisher: Minsk: Publishing Center of BSU
Abstract: At present the deep neural network is the hottest topic in the domain of machine learning and can accomplish a deep hierarchical representation of the input data. Due to deep architecture the large convolutional neural networks can reach very small test error rates below 0.4% using the MNIST database. In this work we have shown, that high accuracy can be achieved using reduced shallow convolutional neural network without adding distortions for digits. The main contribution of this paper is to point out how using simplified convolutional neural network is to obtain test error rate 0.71% on the MNIST handwritten digit benchmark. It permits to reduce computational resources in order to model convolutional neural network.
URI: http://elib.bsu.by/handle/123456789/158552
Appears in Collections:2016. PATTERN RECOGNITION AND INFORMATION PROCESSING (PRIP’2016)

Files in This Item:
File Description SizeFormat 
Golovko_Mikhno_Brich.pdf441,02 kBAdobe PDFView/Open
Show full item record Google Scholar



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.