A Type 2 Neuron Model for Classification and Regression Problems

Abstract

Type 2 fuzzy systems have been under investigation for a while and the projection of type 2 understanding for uncertainty management onto the connectionist models -i.e. neural networks- seems an interesting field of research. This paper considers neurons having multiple bias values defining a new structure that resembles the uncertainty handling capability of type 2 fuzzy models. Such a neuron provides many activation levels that are combined to obtain the neuron response. A neural network with this new model is presented. Several simulation results are shown and the universal approximation property is emphasized.