PARALLEL FUZZY INFERENCE WITH AN OPTOELECTRONIC H-TREE ARCHITECTURE

Fuzzy inference is a method of reasoning with imprecise information. T he mathematical operations of fuzzy inference can be stated in terms o f generalized vector algebra, in which multiplication and summation ar e generalized to MIN and MAX operations. An optoelectronic H-tree arch itecture is ideally suited to perform these generalized vector operati ons in parallel and requires only a simple imaging optical interconnec tion. Appropriate data encodings and electronic circuitry permit large scale, pipelined systems. (C) 1996 Optical Society of America