Knerr S, Personnaz L, Dreyfus G
Ecole Superieure de Phys. et de Chimie Ind. de la Ville de Paris.
IEEE Trans Neural Netw. 1992;3(6):962-8. doi: 10.1109/72.165597.
It is shown that neural network classifiers with single-layer training can be applied efficiently to complex real-world classification problems such as the recognition of handwritten digits. The STEPNET procedure, which decomposes the problem into simpler subproblems which can be solved by linear separators, is introduced. Provided appropriate data representations and learning rules are used, performance comparable to that obtained by more complex networks can be achieved. Results from two different databases are presented: an European database comprising 8700 isolated digits and a zip code database from the US Postal Service comprising 9000 segmented digits. A hardware implementation of the classifier is briefly described.
结果表明，具有单层训练的神经网络分类器可有效地应用于复杂的现实世界分类问题，如手写数字识别。本文介绍了STEPNET程序，该程序将问题分解为可由线性分离器解决的更简单子问题。只要使用适当的数据表示和学习规则，就能获得与更复杂网络相当的性能。文中给出了来自两个不同数据库的结果：一个是包含8700个孤立数字的欧洲数据库，另一个是来自美国邮政服务的包含9000个分段数字的邮政编码数据库。文中还简要描述了分类器的硬件实现。
