{"type":"ScholarlyArticle","title":"Law Discovery using Neural Networks","authors":[{"name":"Kazumi Saito","slug":"kazumi-saito","given":"Kazumi","family":"Saito","affiliation":""},{"name":"Ryohei Nakano","slug":"ryohei-nakano","given":"Ryohei","family":"Nakano","affiliation":""}],"abstract":"This paper proposes a new connectionist approach to numeric law discovery; i.e., neural networks (law-candidates) are trained by using a newly invented second-order learning algorithm based on a quasi-Newton method, called BPQ, and the Minimum Description Length criterion selects the most suitable from lawcandidates. The main advantage of our method over previous work of symbolic or connectionist approach is that it can efficiently discover numeric laws whose power values are not restricted to integers. Experiments showed that the proposed method works well in discovering such laws even from data containing irrelevant variables or a small amount of noise.","doi":null,"url":"https://ijcai.org/proceedings/1997/156","pdf":"https://ijcai.org/proceedings/1997/0156.pdf","markdown":"https://ijcai.org/proceedings/1997/156.md","bibtex":"https://ijcai.org/proceedings/1997/bibtex/156","volume":{"slug":"1997","title":"Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1997","url":"https://ijcai.org/proceedings/1997/","year":1997,"location":"Nagoya, Japan","dates":"","editors":"Martha E. Pollack","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Neural Networks","track":"Neural Networks","number":156,"pages":{"first":1078,"last":1082},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}