Multilayer feedforward networks are universal approximators

This paper rigorously establishes thut standard rnultiluyer feedforward networks with as f&v us one hidden layer using arbitrary squashing functions ure capable of upproximating uny Bore1 measurable function from one finite dimensional space to another to any desired degree of uccuracy, provided sujficirntly muny hidden units are available. In this sense, multilayer feedforward networks are u class of universul rlpproximators. Keywords-Feedforward networks, Universal approximation, Mapping networks, Network representation capability, Stone-Weierstrass Theorem. Squashing functions, Sigma-Pi networks, Back-propagation networks.