Backpropagation Applied to Handwritten Zip Code Recognition
Yann LeCuna, Bernhard E. Bosera, John S. Denkera, D. Hendersona, Richard E. Howarda, W. Hubbarda, L. D. Jackela
- aAT&T Bell Laboratories, Holmdel, NJ 07733 USA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
TL;DRThis paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. (Semantic Scholar)