| Accepted for publicafiof in Mhine Learning Journal, 5/1991 LEARNING TWO.TIERED DESCRIPTIONS OF FLEXIBLE CONCEPTS: (2007) | |||||||||||||||||
Abstract | |||||||||||||||||
| This paper describes a method for learning flexible concepts, by which are meant concepts that lack precise definition and are context-dependent. To describe such concepts, the method employs a two-tiered representation, in which the first tie [ captures explicitly basic concept properties, and the second tier characterizes allowable concept s modifications and context dependency. In the proposed method, the first tier, called Base Concept Representation (BCR), is created in two phases. In phase 1, the AQ-15 rule learning program is applied to i.ndu. ce.a com.ple. te,and con?.iste m concept description from supplied examples. In phase 2, this descnpuon is optmzea accormng. to a domain-dependent quality criterion. The second tier, called the inferential concept interpretanon (ICI), consists of a procedure for flexible matching, and a set of inference rules. The proposed method has been implemented in the POSEIDON system, and experimentally tested on two realworld problems: learning the concept of an acceptable union contract, and learning voting panems of Republicans and Democrats in the U.S. Congress. For comparison, a few other learning methods were also applied to the same problems. These methods included simple variants of exemplar-based learning, and an ID3-type decision tree learning, implemented in the AS. SI,STANT program. In the experiments, POSEIDON generated concept descriptions that were 0ore, more accurate and also substantially simpler than those produced by the other methods. Key words: concept learning, learning imprecs.e concepts, inductive learning, learning flexible concepts, two- | |||||||||||||||||
Publication details | |||||||||||||||||
| |||||||||||||||||