Using Convolutional Neural Network to Recognize Handwritten Digits

Authors

  • Huynh LT Department of Information Technology, Ho Chi Minh City University of Foreign Languages – Information Technology (HUFLIT), Vietnam
  • Phung HT Department of Information Technology, Ho Chi Minh City University of Foreign Languages – Information Technology (HUFLIT), Vietnam
  • Ton TQ Department of Information Technology, Ho Chi Minh City University of Foreign Languages – Information Technology (HUFLIT), Vietnam

Keywords:

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

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.

References

Michael Nielsen, “Neural networks and deep learning”, Sep. 2014, http://neuralnetworkanddeeplearning.com.

Patrice Y. Simard, Dave Steinkraus, John C. Platt, “Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis”, Microsoft Research, 2003

MNIST Database of Handwritten digits, MNIST handwritten digit database, Yann LeCun, Corinna Cortes and Chris Burges, 28 Jan, 2015

Y. LeCun, “Generalization and Network Design Stategies”, Technical Report, 1989.

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

Downloads

Published

2015-05-30

How to Cite

[1]
L. T. Huynh, H. T. Phung, and T. Q. Ton, “Using Convolutional Neural Network to Recognize Handwritten Digits”, Int. J. Comp. Sci. Eng., vol. 3, no. 5, pp. 203–206, May 2015.

Issue

Vol. 3 No. 5 (2015): IJCSE May Edition

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.