Neural computing and production systems

Abstract

The application of neural computing to the problem of matching in production systems is addressed. The computation time required by this problem can be significantly reduced by using the massive parallelism and pattern recognition capabilities available through neural computing. A novel neural computing model, called the ProNet, is introduced and explained in detail. The ProNet is applied to the match phase of the production system interpreter in an attempt to yield a reduction in time and space requirements by matching all of the productions to all of the working memory elements simultaneously. Simulation results are presented. It is shown that, using neural computing via the ProNet, the time required by the match phase can be considerably reduced, and thus the overall time required by the production interpreter can be decreased.<>