Parameter estimation for nonlinear circuits using variants of LMS

In several applications LMS has served as a good tool for estimating the parameters of linear models but the success of LMS in nonlinear models especially in physical systems has not reached its height. In this paper we have developed a Least Mean Square Algorithm that estimates parameters of nonlinear systems considering the noisy input/output relationship. This is accomplished by approximating the given system using a known nonlinear system with unknown parameters called weights that are being approximated using Taylor series expansion. Simulation studies show the validity of the technique developed here in. We have studied coupled oscillator and transistor models as some of the examples of linear and nonlinear system, respectively, whose parameters require to be estimated.