A neural network case-based reasoning and its application

An important factor that plays a major role in determining the performance of a case-based system is the complexity and the accuracy of the case retrieval phase. The nearest neighbor search, knowledge-based method and the inductive approach all suffer from serious drawbacks. This paper examines the possibility of using neural networks as a method of retrieval in such case-based systems. A simple efficient case-based system structure is constructed with neural networks. Also, some algorithms are proposed and tested. The application results show that the approach is efficient.