The comparative synapse: A multiplication free approach to neuro-fuzzy classifiers

This paper introduces a novel synaptic model called a comparative synapse. Compared with traditional synapses, the new model is multiplication free, b eing thus attractive for digital implementations. Our results suggests that in an adaptive layer with binary outputs, the synaptic model does not sign ificantly affect the system performances, provided that the input data is p roperly projected via a nonlinear preprocessor into a separable space, A se t of benchmark classification problems mere considered to illustrate this p roperty for the case of the comparative synapse and a nonlinear preprocesso r defined by fuzzy membership functions.