Possibility function based fuzzy neural networks: case study

This paper describes the framework of a novel approach to fuzzy neural networks, In this approach, a fuzzy neural network accepts a set of possibility functions as well as vectors as input and produces a vector of membership function values as output. A fuzzy neural network implemented in this approach consists of three components: a parameter computing network, a converting layer, and a backpropagation based network. Such a fuzzy neural network shows promise for the classification problems with complex feature sets because it is able to attain comparable classification accuracy with fewer nodes and layers than a backpropagation-based neural network. The authors have implemented a prototype of this approach and applied this prototype to two real world problems: satellite image classification and lithology determination. For both problems, promising results were achieved