Case based reasoning

In rule-based expert systems, knowledge is represented as rules. A rule-based system is one example of deductive reasoning. However, in tasks such as design, diagnosis, planning, management and assessment we often observe a different type of reasoning. An expert facing a new problem is usually reminded of similar situations, recalls their results and perhaps the reasoning. In other words, previous cases are applied to current problems by an analogical reasoning process. Case-based reasoning (CBR) is an area of machine learning research that endeavors to support this process. CBR is based on a memory-centered cognitive model. The basic idea is that past experiences can be remembered and adapted to guide problem solving. Computer systems that solve new problems by analogy with previous ones are called CBR systems, CBR systems base their intelligence and inference on known cases rather than on rules. There are two kinds of CBR systems: problem-solving systems and interpretive systems. A problem-solving system focuses on the construction of solutions suited to the new case by modifying previous case solutions. An interpretive system evaluates and justifies new cases based on the similarities or differences with the previous cases. However, most real-world problems require both types of CBR. AIDS-risky behavior screening, for example, requires both interpreting the behavior and then deriving a conclusion based on the precedents.