AbstractThis paper presents the design of a neural network for signal decomposition problems with application examples. For this class of problems the proposed network has the same dynamics as the Hopfield net, but it is shown to realize theO(M2) connection paths among theMneurons with a number of wires and conductances increasing onlylinearlywith increasingM, i.e. reducing this number byone dimensionwith respect to thequadraticallyincreasing number of wires and conductances required in the Hopfield net.Other advantages of the proposed neural network are discussed in relation to classical examples of decomposition problems. In particular, a new architecture for anN‐bit A/D converter is presented employing 4Nconductances instead of theN(N + 1) Hopfield A/D conductance