{"type":"ScholarlyArticle","title":"Unsupervised Learning by Backward Inhibition","authors":[{"name":"Tomas Hrycej","slug":"tomas-hrycej","given":"Tomas","family":"Hrycej","affiliation":""}],"abstract":"Backward inhibition in a two-layer connectionist network can be used as an alternative to, or an enhancement of, the competitive model for unsupervised learning. Two feature discovery algorithms based on backward inhibition are presented. It is shown that they are superior to the competitive feature discovery algorithm in feature independence and controllable grain. Moreover, the representation in the feature layer is distributed, and a certain \"classification hierarchy\" is defined by the features discovered.","doi":null,"url":"https://ijcai.org/proceedings/1989/27","pdf":"https://ijcai.org/proceedings/1989/0027.pdf","markdown":"https://ijcai.org/proceedings/1989/27.md","bibtex":"https://ijcai.org/proceedings/1989/bibtex/27","volume":{"slug":"1989","title":"Proceedings of the Eleventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1989","url":"https://ijcai.org/proceedings/1989/","year":1989,"location":"Detroit, Michigan, USA","dates":"August 20-25 1989","editors":"N. S. Sridharan","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Parallel and Distributed Processing","track":"Parallel and Distributed Processing","number":27,"pages":{"first":170,"last":174},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}