Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

Winter 1989, Vol. 1, No. 4, Pages 541-551
(doi: 10.1162/neco.1989.1.4.541)
© 1989 Massachusetts Institute of Technology
Backpropagation Applied to Handwritten Zip Code Recognition
Article PDF (619.27 KB)
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.