DESIGN OF FIR LINEAR-PHASE FILTERS WITH DISCRETE COEFFICIENTS USING HOPFIELD NEURAL NETWORKS

A novel method is presented for designing FIR linear phase filters wit h discrete coefficients using Hopfield neural networks. The proposed p rocedure is based on the minimisation of the energy function of the Ho pfield neural network, and can produce a good solution to the design o f FIR linear phase filters with discrete coefficients.