A Constructive RBF Network for Writer Adaptation

Abstract

This paper discusses a fairly general adaptation algorithm which augments a standard neural network to increase its recognition accuracy for a specific user. The basis for the algorithm is that the output of a neural network is characteristic of the input, even when the output is incorrect. We exploit this characteristic output by using an Output Adaptation Module (OAM) which maps this output into the correct user-dependent confidence vector. The OAM is a simplified Resource Allocating Network which constructs radial basis functions on-line. We applied the OAM to construct a writer-adaptive character recognition system for on-line hand-printed characters. The OAM decreases the word error rate on a test set by an average of 45%, while creating only 3 to 25 basis functions for each writer in the test set. To appear: Advances in Neural Information Processing Systems, 9 1 Introduction One of the major difficulties in creating any statistical pattern recognition system is that the statisti...