A COMPARISON STUDY OF BINARY FEEDFORWARD NEURAL NETWORKS AND DIGITAL CIRCUITS

A comparison study was carried out between feedforward neural networks composed of binary linear threshold units and digital circuits. These networks were generated by the regular partitioning algorithm and a m odified Quine-McCluskey algorithm, respectively. The size of both type s of networks and their generalisation properties are compared as a fu nction of the nearest-neighbour correlation in the binary input sets. The ratio of the number of components required by digital circuits and the number of neurons grows linearly for the input sets considered Th e considered neural networks do not outperform digital circuits with r espect to generalisation. Sensitivity analysis leads to a preference f or digital circuits, especially for increasing number of inputs. In th e case of analog input sets, hybrid networks of binary neurons and log ic gates are of interest.