Batch and adaptive Volterra filtering of cubically nonlinear systems with a Gaussian input

Digital techniques of modeling cubically nonlinear systems with a Gaussian input are investigated. Simple batch and adaptive algorithms for estimating the Volterra transfer functions are derived. These algorithms are computationally more efficient than the general (i.e., non-Gaussian and Gaussian) input methods. Computer simulation shows that the proposed adaptive algorithm has a convergence speed comparable to the recursive least-squares (RLS) algorithm, and is applicable to situations where the input is non Gaussian