Backpropagation Applied to Handwritten Zip Code Recognition
Backpropagation Applied to Handwritten Zip Code Recognition
复制标题
DOI：
10.1162/neco.1989.1.4.541
复制
发表时间：
1989-12-01
影响因子：
2.9
通讯作者：
Jackel, L. D.
中科院分区：
文献类型：
--
作者：
LeCun, Y.;Boser, B.;Jackel, L. D.
学习网络的泛化能力可以通过提供任务域的约束来大大增强。本文演示了如何通过网络的体系结构将这些约束集成到反向传播网络中。该方法已成功应用于识别美国邮政局提供的手写邮政编码数字。单个网络学习整个识别操作，从字符的归一化图像到最终分类。
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.