A fuzzy neural model for target recognition

Summary form only given, as follows. A mathematical model of a multilevel, multilayer neural network was developed which uses fuzzy theory for classification. This model would allow imprecise or incomplete knowledge gained at one level of the network to be forwarded as additional input to the next level of the network. Fuzzy theory makes it possible to interpret the information in a more general form for developing methods in pattern clustering and recognition. It is believed this approach will incorporate human thinking and decision making into neural networks.<
>