Deep Evolving Stacking Convex Cascade Neo-Fuzzy Network and Its Rapid Learning

Abstract

A deep evolving stacking convex neo-fuzzy network is proposed. It is a feedforward cascade hybrid system, the layers-stacks of which are formed by generalized neo-fuzzy neurons that implement Wang-Mendel fuzzy reasoning. The optimal in the sense of speed algorithms are proposed for its learning. Due to independent layer adjustment, parallelization of calculations in non-linear synapses and optimization of learning processes, the proposed network has high speed that allows to process information in online mode.