Part of Advances in Neural Information Processing Systems 9 (NIPS 1996)
Time series prediction is one of the major applications of neural net(cid:173) works. After a short introduction into the basic theoretical foundations we argue that the iterated prediction of a dynamical system may be in(cid:173) terpreted as a model of the system dynamics. By means of RBF neural networks we describe a modeling approach and extend it to be able to model instationary systems. As a practical test for the capabilities of the method we investigate the modeling of musical and speech signals and demonstrate that the model may be used for synthesis of musical and speech signals.