A Learning Algorithm for Applying Cohen's Models to System Identification

In this paper we extend the models discussed by Cohen (1992) by introducing an input term. This allows the resulting models to be utilized for system identification tasks. We prove that this model is stable in the sense that a bounded input leads to a bounded state when a minor restriction is imposed on the Lyapunov function. By employing this stability result, we are able to find a learning algorithm which guarantees convergence to a set of parameters for which the error between the model trajectories and the desired trajectories vanishes. 1 Introduction In this paper we present a straightforward extension of the models introduced by Cohen (1992). Specifically we introduce an additional term to allow for an external input. This allows these models to be utilized for system identification tasks. By imposing a minor restriction on the Lyapunov functions constructed in Cohen (1992), we prove that this extended model is stable in the sense that a bounded input leads to a bounded state. U..