Transputer based Hopfield neural net emulation system for pattern recognition

A transputer-base Hopfield neural net emulation system for pattern recognition is presented. The Hopfield neural net is constructed by the transputers in mesh architectures. The cross-points of the mesh represent the basic processing element of the neural net. The concurrent OCCAM language is used for software programming and data transfer control. Using this system, certain specific pattern recognition is realized. It is shown that the performance of pattern recognition with a Hopfield neural net is encouraging and acceptable