Backpropagation Applied to Handwritten Zip Code Recognition
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.
Summary¶
Demonstrates end-to-end handwritten digit recognition using a backpropagation network whose local receptive fields and shared weights encode spatial prior knowledge. The architecture learns directly from normalized U.S. Postal Service digit images and shows how task-specific constraints improve generalization.