{"type":"ScholarlyArticle","title":"Learning on the Phase Transition Edge","authors":[{"name":"Alessandro Serra","slug":"alessandro-serra","given":"Alessandro","family":"Serra","affiliation":""},{"name":"Attilio Giordana","slug":"attilio-giordana","given":"Attilio","family":"Giordana","affiliation":""},{"name":"Lorenza Saitta","slug":"lorenza-saitta","given":"Lorenza","family":"Saitta","affiliation":""}],"abstract":"A previous research has shown that most learning strategies fail to learn relational concepts when descriptions involving more than three variables are required. The reason resides in the emergence of a phase transition in the covering test. After an in depth analysis of this aspect, this paper proposes an alternative learning strategy, combining a Monte Carlo stochastic search with local deterministic search. This approach offers two main benefits: on the one hand, substantial advantages over more traditional search algorithms, in terms of increased learning ability, and, on the other, the possibility of an a-priori estimation of the cost for solving a learning problem, under specific assumptions about the target concept.","doi":null,"url":"https://ijcai.org/proceedings/2001/126","pdf":"https://ijcai.org/proceedings/2001/0126.pdf","markdown":"https://ijcai.org/proceedings/2001/126.md","bibtex":"https://ijcai.org/proceedings/2001/bibtex/126","volume":{"slug":"2001","title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2001","url":"https://ijcai.org/proceedings/2001/","year":2001,"location":"Seattle, Washington, USA","dates":"","editors":"","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":126,"pages":{"first":921,"last":925},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}