论文信息 - Handwritten Digit Recognition with a Back-Propagation Network

Handwritten Digit Recognition with a Back-Propagation Network

We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task. The input of the network consists of normalized images of isolated digits. The method has 1% error rate and about a 9% reject rate on zipcode digits provided by the U.S. Postal Service.

[1] Kunihiko Fukushima,et al. Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[2] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[3] Lawrence D. Jackel,et al. Large Automatic Learning, Rule Extraction, and Generalization , 1987, Complex Syst..

[4] Stefano Patarnello,et al. Learning Networks of Neurons with Boolean Logic , 1987 .

[5] Isabelle Guyon,et al. Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[6] Léon Bottou,et al. Sn: A simulator for connectionist models , 1988 .

[7] Yann LeCun,et al. Generalization and network design strategies , 1989 .

[8] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[9] Naftali Tishby,et al. Consistent inference of probabilities in layered networks: predictions and generalizations , 1989, International 1989 Joint Conference on Neural Networks.

[10] Yann LeCun,et al. Optimal Brain Damage , 1989, NIPS.