A Neural Network Truth Maintenance System

A novel approach using neural networks to solve expert system problems is presented in this paper. Facts are represented by neurons and their interconnections form the knowledge base. The Truth Maintenance System neural network arrives at a valid solution provided the solution exists. A valid solution is a consistent set of facts. If the solution does not exist the network limit cycles. An experimental setup was built and tested using conventional integrated circuits. The hardware design is suitable for VLSI implementation for large, real-time problems.