Optical expert system based on matrix-algebraic formulation

This paper describes an expert system paradigm based on matrix algebra. The knowledge base of the expert system is stored in binary matrices, while the learning and inference processes are done by matrix algebra operations. This method is highly parallel and can take full advantage of the inherent parallelism and connectivity of optics. An optoelectronic architecture that implements this system is presented. In addition, the method is compared with the sequential search methods written in the programming language PROLOG to illustrate their differences and commonalities.