This paper proposes an enhanced RBF network that enhances learning algorithms between input layer and middle layer and between middle layer and output layer individually for improving the efficiency of learning. The proposed network applies ART2 network as the learning structure between input layer and middle layer. And the auto-tuning method of learning rate and momentum is proposed and applied to learning between middle layer and output layer, which arbitrates learning rate and momentum dynamically by using the fuzzy control system for the arbitration of the connected weight between middle layer and output layer. The experiment for the classification of number patterns extracted from the citizen registration card shows that compared with conventional networks such as delta-bar-delta algorithm and the ART2-based RBF network, the proposed method achieves the improvement of performance in terms of learning speed and convergence.

This paper proposes a nonlinear signal processing by using a three layered network which is trained with self-organized clustering and supervised learning. The network consists of three layers, i.e., self-organized layer, an evaluation layer and an output layer. Since the evaluation layer is designed as a simple perceptron network and the output layer is designed as a fixed weight linear node, the training complexity is the same as a conventional one consisting of self-organized clustering and a simple perceptron network. In other words, quite high speed training can be realized. Generally speaking, since the data range is arbitrary large in signal procession, the network shoulk cover this range and output a value as accurately as possible. However, it may be hard for only a node in the network to output these data. Instead of this mechanism, if this dynamic range is covered by using several nodes, the complexity of each node is reduced and the associated range is also limited. This results on the higher performance of the network than conventional RBFs. This paper introduces a new non-linear spectrum estimation which consists of LPC analysis and RBF network. It is shown that accuracy spectrum envelopes can be obtained since a new RBF network can estimate some nonlinearities in a speech production.