개선된 RBF신경회로망에 비선형 시스템의 동정

초록

In this paper, RBF(Radial Basis Function) Neural Network is suggested for the identification of a nonlinear system. RBF is the model which is based on the locally tuned responses of biological neurons. This model has very fast learning time and is capable of identifying a system behavior with noisy or distorted information. Suggested RBF neural network proposes a way to choose parameters which determine RBF to use before learning, whereas with existing RBF neural networks, parameters are determined heuristically. Another key feature of this model is to calculate appropriate total number of RBF in hidden layer by forward selection method.