Learning dynamical systems in a stationary environment - Texas A&M University (TAMU) Scholar

We consider the problem of learning the input-output relation of a dynamical system from noisy data. Our method rests on the use of a smooth simultaneous estimator which generalizes the standard empirical estimator. In a stationary environment, our algorithm is shown to select a model which exhibits the Probably Approximately Correct (PAC) property under very mild conditions. This contribution should be thought of as a first attempt to extend concepts developed in learning theory to the field of system identification where, due to the presence of the system dynamics, the typical i.i.d. assumption on the data made in learning theory is not satisfied. © 1998 Elsevier Science B.V. All rights reserved.

Learning dynamical systems in a stationary environment Academic Article