INRECA: A Seamlessly Integrated System Based on Inductive Inference and Case-Based Reasoning

摘要: This paper focuses on integrating inductive inference and case-based reasoning. We study integration along two dimensions: Integration of methods with based general domain knowledge, problem solving incremental learning from experience. In the Inreca system, we perform reasoning as well tdidt (Top-Down Induction Decision Trees) classification by using same data structure called tree. extract decision knowledge a algorithm to improve both similarity assessment determining optimal weights, speed overall system learning. The integrated implemented evolves smoothly application development time pure approach, where each particular case is piece more approach some subsets cases are generalised into abstract knowledge. Our proposed driven needs concrete pre-commercial real diagnostic applications. evaluate database insurance risk for cars an involving forestry management in Ireland.