This paper attempts to enhance the dynamic performance of a shunt-type active power filter. The predictive and adaptive properties of artificial neural networks (ANNs) are used for fast estimation of the compensating current. The dynamics of the dc-link voltage is utilized in a predictive controller to generate the first estimate followed by convergence of the algorithm by an adaptive ANN (adaline) based network. Weights in adaline are tuned to minimize the total harmonic distortion of the source current. Extensive simulations and experimentations confirm the validity of the proposed scheme for all kinds of load (balanced and unbalanced) for a three-phase three-wire system.