The process of computing pattern recognition using energy of type of wave computer pattern recognition and dynamic process to produce a mathematical model of a dynamic image P.For use in pattern recognition computing

摘要

Pattern-recognition computing can be accomplished using wave-type or other types of energy. In pattern-recognition computing which uses a plurality of wave-type energy input patterns modulated with quantized information (10, 11, 12, 13), energy from the patterns combines to produce interference-based dynamic images (31, 31A). Component parts of a dynamic image are separated and recombined to produce logic and other computing process outputs (28, 29). To produce a coordinated set of optics for pattern-recognition computing, waveforms at pixel-sized image components of the dynamic image are chosen to become contributors to the combined output if they will contribute (or can be modified to contribute) in a positive manner to a combined output waveform that obeys the logic rules of the device being produced. Iterative changes in input pattern characteristics are used to optimize the coordinated optics. Pattern-recognition computing can also use special interference and frequency-multiplexed logic.