Self-organization neurons blocks networks [sic]

Abstract

Presents a new class of higher-order feedforward neural networks, called self-organized neuron block networks (SNBNs). SNBN networks are based on the inductive learning method (also called self-organization). These new networks are shown to uniformly approximate any continuous function with an arbitrary degree of accuracy. An SNBN provides a natural mechanism for incremental network growth, and we develop a constructive algorithm based on the inductive learning method for the network. Simulation results of forecasting, approximations of nonlinear functions and approximations of multivariate polynomials are given in order to highlight the capability of the network.