Neural Network Recognizer for Hand-Written Zip Code Digits
Abstract
This paper describes the construction of a system that recognizes hand-printed digits, using a combination of classical techniques and neural-net methods. The system has been trained and tested on real-world data, derived from zip codes seen on actual U.S. Mail. The system rejects a small percentage of the examples as unclassifiable, and achieves a very low error rate on the remaining examples. The system compares favorably with other state-of-the art recognizers. While some of the methods are specific to this task, it is hoped that many of the techniques will be applicable to a wide range of recognition tasks.
Cite
Text
Denker et al. "Neural Network Recognizer for Hand-Written Zip Code Digits." Neural Information Processing Systems, 1988.Markdown
[Denker et al. "Neural Network Recognizer for Hand-Written Zip Code Digits." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/denker1988neurips-neural/)BibTeX
@inproceedings{denker1988neurips-neural,
title = {{Neural Network Recognizer for Hand-Written Zip Code Digits}},
author = {Denker, John S. and Gardner, W. R. and Graf, Hans Peter and Henderson, Donnie and Howard, R. E. and Hubbard, W. and Jackel, L. D. and Baird, Henry S. and Guyon, Isabelle},
booktitle = {Neural Information Processing Systems},
year = {1988},
pages = {323-331},
url = {https://mlanthology.org/neurips/1988/denker1988neurips-neural/}
}