Local minima effects on the transient performance of non-linear blind equalizers

The computational requirements and the transient performance of several non-linear blind equalizers are compared in the case of transmission over linear and non-linear channels. The multilayer perceptron (MLP), the radial-basis-function network (RBF), the polynomial perceptron (PP) and two recently proposed non-linear structures (see Destro Filho, J.B., et al., Proc. GLOBECOM'96, p.196-200, 1996; Proc. GLOBECOM'99, 1999) are simulated. These equalizers are also compared to two classical benchmarks: the Volterra filter and Godard algorithm. A criterion for assessing the impact of parameter initialization (filter coefficients and synaptic weights) on the transient performance is proposed and evaluated. The results establish guidelines for choosing a particular non-linear blind equalizer when the trade-off between robustness to local minima problems and computational requirements must be satisfied.