A temporal neural network model for constructing connectionist expert system knowledge bases

Abstract

This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications. A temporal backpropagation algorithm which supports the model has been developed. The model along with the temporal backpropagation algorithm makes it extremely practical to define any artificial neural network application. Also, an approach that can be followed to decrease the memory space used by weight matrix has been introduced. The algorithm was tested using a medical connectionist expert system to show how best we describe not only the disease but also the entire course of the disease. The system is a medical diagnosis expert system which was developed to run on microcomputers using Pascal programming language. A new version of the system written using C programming language is currently under development. The system was first trained using a pattern that was encoded from the expert system knowledge base rules. Then series of experiments were carried out using the temporal model and the temporal backpropagation algorithm. The experiments indicated that the algorithm produces correct results and the model correctly represents explicit sequences of time.