论文信息 - Experimental Study of an Evaluation Function for Cases Imperfectly Explained

Experimental Study of an Evaluation Function for Cases Imperfectly Explained

This paper describes an evaluation function which deals with similarities and dissimilarities in cases imperfectly explained. Our explanation-based evaluation function represents an alternative to other approaches that use case explanations for selection and retrieval of past cases. This function is used by a diagnosis system called RECIDEclinic. We present the experimental results obtained in the domain of neurologic diseases. These results illustrate the role of similarity and dissimilarity terms as they are defined within our framework.

[1] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2] Janet L. Kolodner,et al. Case-Based Reasoning , 1989, IJCAI 1989.

[3] Michael J. Pazzani,et al. Creating a memory of causal relationships - an integration of empirical and explanation-based learning methods , 1990 .

[4] Christopher K. Riesbeck,et al. Inside Case-Based Reasoning , 1989 .

[5] Manuela Veloso. Learning by analogical reasoning in general problem-solving , 1992 .

[6] Koton Phyllis,et al. Using experience in learning and problem solving , 1988 .

[7] Kristian J. Hammond,et al. Case-based planning: an integrated theory of planning, learning and memory , 1986 .

[8] Ernesto Costa,et al. A Similarity Metric for Retrieval of Cases Imperfectly Explained , 1993, EWCBR.

[9] William Mark,et al. Explanation-Based Indexing of Cases , 1988, AAAI.

[10] Christopher K. Riesbeck,et al. Experience, Memory and Reasoning , 1986 .

[11] Ray Bareiss,et al. Concept Learning and Heuristic Classification in WeakTtheory Domains , 1990, Artif. Intell..

[12] Michael John Pazzani. Learning causal relationships: an integration of empirical and explanation-based learning methods , 1988 .

[13] Janet L. Kolodner,et al. Retrieval and organizational strategies in conceptual memory: a computer model , 1980 .