Single multiplicative neuron model based on generalized mean

Abstract

This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean single multiplicative neuron (GMSMN) model. The structure of this model is simpler than higher-order neuron model. The simulation results show that the performance of the proposed neuron model is better than SMN model.