Abstract
We describe two neural-net approaches to digit recognition. One method uses a neural-network chip to perform line thinning and local feature extraction. This preprocessing stage was designed by hand and did not involve any learning. However, automatic learning was used in the final classification step. The chip can process about 100 characters/sec, but the interface to the host computer limits the throughput to about 1 character/sec.
The other method uses constrained automatic learning on pixel images with no preprocessing other than segmentation and size-normalization. It appears that good generalization performance cannot be obtained unless some a priori knowledge about the task is built into the system. This paper demonstrates how such knowledge can be integrated into a back-propagation network by providing hints and constraints on the architecture. Most of the computational burden of this method can be borne by a digital signal processor, resulting in a throughput of about 10 characters/sec.
Both methods have 1% error rate and about a 12–13% reject rate when trained on 7300 digits taken from U.S. Zipcodes and tested on 2000 such digits. These results appear to be at the state-of-the-art in handwritten digit recognition.
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
L.-Y. Bottou and Y. le Cun. Sn: A simulator for connectionist models. In Proceedings of NeuroNimes 88, Nimes, Rrance, 1988.
R. G. Casey. Moment normalization of handprinted characters. IBM Journal of Research and Development, 548, 1970.
J. Denker, D. Schwartz, B. Wittner, S. A. Solla, R. Howard, L. Jackel, and J. Hop-field. Large automatic learning, rule extraction and generalization. Complex Systems, 1:877–922, 1987.
J. S. Denker, W. R. Gardner, H. P. Graf, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel, H. S. Baird, and I. Guyon. Neural network recognizer for hand-written zip code digits. In D. Touretzky, editor, Advances in Neural Information Processing Systems, pages 323–331. Morgan Kaufmann, 1989.
H.-P. Graf, W. Hubbard, L. D. Jackel, and P. G. de Vegvar. A cmos associative memory chip. In Proc. IEEE First International Conference on Neural Networks, pages III-461. IEEE, 1987. San Diego, CA.
D. H. Hubel and T. N. Wiesel. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. Journal of Physiology, 160:106–154, 1962.
Y. le Cun. Modèles CAnnexionnistes de VApprentissage. PhD thesis, Université Pierre et Marie Curie, Paris, Prance, 1987.
Y. le Cun. Generalization and network design strategies. In R. Pfeifer, Z. Schreter, F. Fogelman, and L. Steels, editors, Connectionism in Perspective, Zurich, Switzerland, 1989. Elsevier.
N. J. Naccache and R. Shingal. Spta: A proposed algorithm for thinning binary patterns. IEEE Trans. Systems, Man, and Cybernetics, SMC-14:409, 1984.
W. C. Naylor. Some studies in the interactive design of character recognition systems. IEEE Transaction on Computers, page 1075, 1971.
S. Patarnello and P. Carnevali. Learning networks of neurons with boolean logic. Europhysics Letters, 4(4):503–508, 1987.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. In Parallel distributed processing: Explorations in the microstructure of cognition, volume I., Bradford Books, Cambridge, MA, 1986.
N. Tishby, E. Levin, and S. A. Solla. Consistent inference of probabilities in layered networks: Predictions and generalization. In Proceedings of the International Joint Conference on Neural Networks, Washington DC, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Le Cun, Y. et al. (1990). Handwritten Digit Recognition: Applications of Neural Net Chips and Automatic Learning. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive