Abstract
A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen’s self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
DARPA: DARPA Neural Network Study. AFCEA International Press (1988) 60
Jain, L.C., Lazzerini, B. (eds.): Knowledge-based Intelligent Techniques in Character Recognition. CRC Press, Boca Raton FL (1999)
Kohonen, T.: Self-Organizing Maps. Springer-Verlag, Berlin (1995)
LeCun, Y., Jackel, L.D., Bottou, L., Brunot, A., Cortes, C., Denker, J.S., Drucker, H., Guyon, I., Muller, U.A., Sackinger, E., Simard, P., Vapnik, V.: Comparison of Learning Algorithms for Handwritten Digit Recognition. In: Fogelman, F., Gallinari, P. (eds.): Proc. 5th Int. Conf. on Artificial Neural Networks (1995) 53–60
Wentink, M.: Master-Slave Kohonen Network Applied to Digit Recognition. Internal Report BSC-021N95, University of Twente (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
van der Zwaag, BJ. (2001). Handwritten Digit Recognition: A Neural Network Demo. In: Reusch, B. (eds) Computational Intelligence. Theory and Applications. Fuzzy Days 2001. Lecture Notes in Computer Science, vol 2206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45493-4_75
Download citation
DOI: https://doi.org/10.1007/3-540-45493-4_75
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42732-2
Online ISBN: 978-3-540-45493-9
eBook Packages: Springer Book Archive