Open Access   Article Go Back

Using Convolutional Neural Network to Recognize Handwritten Digits

Loc Thanh Huynh1 , Hung Thang Phung2 , Toai QuangTon3

Section:Research Paper, Product Type: Journal Paper
Volume-3 , Issue-5 , Page no. 203-206, May-2015

Online published on May 30, 2015

Copyright © Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

View this paper at   Google Scholar | DPI Digital Library

XML View
PDF Download

How to Cite this Paper

  • IEEE Citation
  • MLA Citation
  • APA Citation
  • BibTex Citation
  • RIS Citation

IEEE Style Citation: Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon, “Using Convolutional Neural Network to Recognize Handwritten Digits,” International Journal of Computer Sciences and Engineering, Vol.3, Issue.5, pp.203-206, 2015.

MLA Style Citation: Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon "Using Convolutional Neural Network to Recognize Handwritten Digits." International Journal of Computer Sciences and Engineering 3.5 (2015): 203-206.

APA Style Citation: Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon, (2015). Using Convolutional Neural Network to Recognize Handwritten Digits. International Journal of Computer Sciences and Engineering, 3(5), 203-206.

BibTex Style Citation:
@article{Huynh_2015,
author = {Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon},
title = {Using Convolutional Neural Network to Recognize Handwritten Digits},
journal = {International Journal of Computer Sciences and Engineering},
issue_date = {5 2015},
volume = {3},
Issue = {5},
month = {5},
year = {2015},
issn = {2347-2693},
pages = {203-206},
url = {https://www.ijcseonline.org/full_paper_view.php?paper_id=504},
publisher = {IJCSE, Indore, INDIA},
}

RIS Style Citation:
TY - JOUR
UR - https://www.ijcseonline.org/full_paper_view.php?paper_id=504
TI - Using Convolutional Neural Network to Recognize Handwritten Digits
T2 - International Journal of Computer Sciences and Engineering
AU - Loc Thanh Huynh, Hung Thang Phung ,Toai QuangTon
PY - 2015
DA - 2015/05/30
PB - IJCSE, Indore, INDIA
SP - 203-206
IS - 5
VL - 3
SN - 2347-2693
ER -

VIEWS PDF XML
2564 2358 downloads 2401 downloads
  
  
           

Abstract

An artificial neural network (ANN) or simply “neural net” is a data processing system consisting of a large number of simple, highly interconnected processing elements in an architecture inspired by the structure of the human brain. Hence, neural networks are often capable of doing things which humans or animals do well but which conventional computers often do poorly. This paper presents a brief introduction to convolutional neural network(CNN) – a neural network with a special structure and describes how it works to recognize handwritten digits.After a network was trained by training dataset from MNIST database, it can classify 10,000 examples from MNIST testing dataset within 35 secondsand achieve3.25% error rate.

Key-Words / Index Term

Neural Network, Convolutional Neural Network, Feed forward, Back propagation, Classification

References

[1] Michael Nielsen, “Neural networks and deep learning”, Sep. 2014, http://neuralnetworkanddeeplearning.com.
[2] Patrice Y. Simard, Dave Steinkraus, John C. Platt, “Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis”, Microsoft Research, 2003
[3] MNIST Database of Handwritten digits, MNIST handwritten digit database, Yann LeCun, Corinna Cortes and Chris Burges, 28 Jan, 2015
[4] Y. LeCun, “Generalization and Network Design Stategies”, Technical Report, 1989.
[5] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, “Gradient-Based Learning Applied to Document Recognition”, Proceedings of the IEEE, Vol-86, Issue-11, Page no (2278-2324), 1998