HANDWRITTEN DIGIT RECOGNITION BY NEURAL NETWORKS WITH SINGLE-LAYER TRAINING

We show 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. We introduce the STEPNET procedure, which decomposes the problem into simpler subproblems which can be solved by linear separators. Provided appropriate data representations and learning rules are used, performances which are comparable to those obtained by more complex networks can be achieved. We present results from two different data bases: a European data base comprising 8700 isolated digits, and a zip code data base from the U.S. Postal Service comprising 9000 segmented digits. A hardware implementation of the classifier is briefly described.