An integrated shell for developing connectionist expert systems

This paper presents a prototype shell for developing neural network expert systems. The shell, structured around the concept of a neural logic network element (netel), is aimed at preserving semantic structure of the expert system rules whilst incorporating learning capability of neural networks into the inferencing mechanism. Using this architecture, every rule of the knowledge base is represented by a netel. These netels are dynamically linked up to form the rule-tree during the inferencing process. The system is also able to adjust its inference strategy according to different users and situations. The prototype shell is used to build an advisory expert system for bond trading. The system yields promising results, thus demonstrating the strengths of the above-mentioned architecture.