Process of Learning Discrete Dynamical Systems by Recurrent Neural Networks.

This paper considers the learning of discrete dynamical systems using recurrent neural networks. The discussion is based on the theory of the probabilistic descent method, and the learning algorithms are compared by numerical experiment. In the discussion based on the theory of the probabilistic descent method, it is shown that, from the viewpoint of the learning speed in the early stage of the learning, is equivalent to the backpropagation method with a large learning constant. For the case where the variable is not constrained to the value of the teacher signal and a chaotic time series with a large Lyapunov exponent is to be learned, it is found that the effect of the recurrent connections is not manifest at the early stage of the learning but the learning is accelerated with the progress of the learning by the fluctuation caused by the chaos. [ABSTRACT FROM AUTHOR]