A neural network based expert system model

Summary form only given. The architecture of an expert system model (ESM) using artificial neural networks is proposed. The proposed model effectively supports the necessary components of an expert system, such as user interface facility, knowledge base, inference engine, and explanation system. The ESM consists of several orders of simple neural networks, each realizing a simple task. These simple neural networks are organized vertically, thereby achieving a second level of parallelism. A novel way to handle both forward and backward chaining reasoning mechanisms has been devised. A secondary network model monitors the reasoning patterns of the primary model. Once adequately learned, this secondary network, known as the learning network, can generate reasons based on experience this would eliminate the need for unnecessary searching, and thus enhance the response time