Backpropagation Applied to Handwritten Zip Code Recognition
Yann LeCun, Bernhard E. Boser, John S. Denker et al. · Neural Computation · 1989
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.
Cited by 11,874 works. doi:10.1162/neco.1989.1.4.541
Authors
References
- Learning Internal Representations by Error Propagation
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- Sn: A simulator for connectionist models
- What Size Net Gives Valid Generalization?
- Improving the convergence of back-propagation learning with second-order methods
- Large Automatic Learning, Rule Extraction, and Generalization.
- Generalization and network design strategies
- Consistent inference of probabilities in layered networks: predictions and generalizations
- Learning Networks of Neurons with Boolean Logic