Dendritic Neuron Model and Its Capability of Approximation

Abstract

Recently, an artificial neural network (ANN) named dendritic neuron model has been proposed which mimics the nonlinear interaction in the signal processing in a neuron. in order to research the approximation performance of this model, this paper use the mathematical theory to prove that single dendritic neuron model neuron is able to approximate any Borel measurable function to any desired degree of accuracy.