Learning performance of a neurocomputer for nonlinear dynamical system identification

This paper investigates the learning performance of a RICOH neurocomputer R N-2000 for the identification problem of input and output map of a discrete nonlinear dynamical system. The results obtained show capability of on-chi p learning, which is essential for many neural applications such as machine learning and control where realtime adaptation is required, In this paper, the method to use a neurocomputer is briefly presented for a nonlinear ide ntification problem. The main significance of this research is to obtain a further guideline for designing a primitive artificial blain for robotics. (C) 2001 Elsevier Science Inc. All rights reserved.