Purely neural, rule-based diagnostic systems. II. Uncertain reasoning

Abstract

This article describes neural mechanisms for carrying out forms of uncertain reasoning that are frequently applied in diagnostic problem-solving. These include various sorts of causal and probabilistic reasoning, as well as the updating of certainty measures. the control and synchronization functions that are needed to schedule these inferential processes are carried out by a neural network, too. A concluding section is devoted to discussing the role of learning in neural diagnostic systems. © 1995 John Wiley & Sons, Inc.