USE OF NEURAL NETWORKS AS MEDICAL DIAGNOSIS EXPERT-SYSTEMS

A major bottleneck in building expert systems is the process of acquir ing the required knowledge in the form of production rules. A novel cl ass of neural networks is proposed to articulate the knowledge it lear ned from a set of examples. It provides an appealing solution to the p roblem of knowledge acquisition. After training, the knowledge embedde d in the numerical weights of trained neural networks can be easily ex tracted and represented in the form of production rules, The approach is demonstrated by an example of a hypothesis regarding the pathophysi ology of diabetes.