A Solution for the N-bit Parity Problem Using a Single Translated Multiplicative Neuron

摘要

A solution to the N-bit parity problem employing a single multiplicative neuron model, called translated multiplicative neuron (π t -neuron), is proposed. The π t -neuron presents the following advantages: (a) ∀N≥1, only 1 π t -neuron is necessary, with a threshold activation function and parameters defined within a specific interval; (b) no learning procedures are required; and (c) the computational cost is the same as the one associated with a simple McCulloch-Pitts neuron. Therefore, the π t -neuron solution to the N-bit parity problem has the lowest computational cost among the neural solutions presented to date.