An heuristic pattern correction scheme for GRNNs and its application to speech recognition

In an online learning environment where optimal recognition performance over the newly encountered patterns is required, a robust incremental learning procedure is necessary to re-configure the entire neural network without affecting the stored information. In this paper, an heuristic pattern correction scheme based upon an hierarchical data partitioning principle is proposed for digit word recognition. This scheme is based upon general regression neural networks (GRNNs) with initial centroid vectors obtained by graph theoretic data-pruning methods. Simulation results show that the proposed scheme can perfectly correct the mis-classified patterns and hence improves the generalisation performance without affecting the old information. Moreover, it is also established that the initial setting of radial basis functions (RBFs) based upon graph theoretic data-pruning methods yields better performance than those obtained by k-means and learning vector quantisation (LVQ) methods