Neural networks designed on approximate reasoning architecture and their applications.

The NARA (neural networks based on approximate reasoning architecture) model is proposed and its composition procedure and evaluation are described. NARA is a neural network (NN) based on the structure of fuzzy inference rules. The distinctive feature of NARA is that its internal state can be analyzed according to the rule structure, and the problematic portion can be easily located and improved. The ease with which performance can be improved is shown by applying the NARA model to pattern classification problems. The NARA model is shown to be more efficient than ordinary NN models. In NARA, characteristics of the application task can be built into the NN model in advance by employing the logic structure, in the form of fuzzy inference rules. Therefore, it is easier to improve the performance of NARA, in which the internal state can be observed because of its structure, than that of an ordinary NN model, which is like a black box. Examples are introduced by applying the NARA model to the problems of auto adjustment of VTR tape running mechanisms and alphanumeric character recognition.