Stochastic gradient algorithm for multi-input multi-output Hammerstein FIR-MA-like systems using the data filtering

This paper presents a data filtering based stochastic gradient algorithm for estimating the parameters of multivariable Hammerstein FIR-MA-like systems. By filtering the input and output data, the FIR-MA-like model is transformed into a controlled autoregressive model. The examples confirm that the proposed algorithm is more accurate and has a better performance than the stochastic gradient algorithm.