{"type":"ScholarlyArticle","title":"Learning Concept Descriptions from Examples with Errors","authors":[{"name":"Jakub Segen","slug":"jakub-segen","given":"Jakub","family":"Segen","affiliation":""}],"abstract":"This paper presents a scheme for learning complex descriptions, such as logic formulas, from examples with errors. The basis for learning is provided by a selection criterion which minimizes a combined measure of discrepancy of a description with training data, and complexity of a description. Learning rules for two types of descriptors are derived: one for finding descriptors with good average discrimination over a set of concepts, second for selecting the best descriptor for a specific concept. Once these descriptors are found, an unknown instance can be identified by a search using the descriptors of the first type for a fast screening of candidate concepts, and the second for the final selection of the closest concept.","doi":null,"url":"https://ijcai.org/proceedings/1985/122","pdf":"https://ijcai.org/proceedings/1985/0122.pdf","markdown":"https://ijcai.org/proceedings/1985/122.md","bibtex":"https://ijcai.org/proceedings/1985/bibtex/122","volume":{"slug":"1985","title":"Proceedings of the Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1985","url":"https://ijcai.org/proceedings/1985/","year":1985,"location":"Los Angeles, California, USA","dates":"","editors":"Aravind Joshi","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Learning and Acquisition","track":"Learning and Acquisition","number":122,"pages":{"first":634,"last":635},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}