Development of a hyper-parallel optical fuzzy-neural network using images

A hyper-parallel fuzzy-neural network system that uses optical images to infer conclusions is proposed. This system is formed on the basis of the idea of the optical fuzzy inferring system proposed by the author. The hyper-parallel neural network can transform input data applied to a great number of input units into outputs generated from a great number of output units. This paper shows the fundamental optical architectures of the fuzzy-neuro system and the hyper-parallel fuzzy-neural network. Pattern recognition of numerical letters by the fuzzy-neuro system and the calculation of correlation between two-dimensional patterns by the hyper-parallel fuzzy-neural network are also demonstrated