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, being thus attractive for digital implementations. Our results suggests that in an adaptive layer with binary outputs, the synaptic model does not significantly affect the system performances, provided that the input data is properly projected via a nonlinear preprocessor into a separable space. A set of benchmark classification problems were considered to illustrate this property for the case of the comparative synapse and a nonlinear preprocessor defined by fuzzy membership functions.