A spiking neural network architecture for nonlinear function approximation

Multilayer perceptrons have received much attention due to their universal approximation capabilities. Normally such models use real valued signals, although they are loosely based on biological neuronal networks which encode signals using spike trains. Spiking neural networks are of interest from both a biological point of view, but also from a method of robust signalling in particularly noisy or difficult environments. From a signal processing perspective, it is important to consider networks based on spike trains. A basic question that needs to be considered, is what type of architecture can be used to provide universal function approximation capabilities in spiking networks? We propose a spiking neural network architecture using both integrate and fire units as well as delays which is capable of approximating a real valued function mapping to within a finite degree of accuracy.