Neural network minimization techniques for multistage orthogonal QMF filters with vanishing moments

In this paper a feedforward neural network is used to address multi-stage decomposition signal compression. The neural network uses back-propagation to update the filter coefficients of all stages simultaneously in each iteration. Back propagation is the vehicle that allows the optimization to proceed in a forward and backward direction, thus achieving a better signal compression than forward only stage by stage compression. In addition, the paper will address how to use the algorithm when all stages are constrained to be identical; a restriction that results in a wavelet type decomposition.