{"type":"ScholarlyArticle","title":"Marker-Passing and Microfeatures","authors":[{"name":"James A. Hendler","slug":"james-a-hendler","given":"James A.","family":"Hendler","affiliation":""}],"abstract":"The cognitive modeling community is presently divided between two different approaches to the •pread of activation through networks. One school holds that .ymbolic information mut be procagated, the other that numeric weights are used and activation spreads in a more analog manner . In this paper we describe a mechanism which allows the two processes to be merged via the introduction into the .ymboJic network of a dejininf•C/aGrllcferiftic link which is affects the spread of the .ymbolic information in a manner resembling local connectionist computations . We demonstrate that the combined .ystem is more powerful than either or the separate models alone.","doi":null,"url":"https://ijcai.org/proceedings/1987/29","pdf":"https://ijcai.org/proceedings/1987/0029.pdf","markdown":"https://ijcai.org/proceedings/1987/29.md","bibtex":"https://ijcai.org/proceedings/1987/bibtex/29","volume":{"slug":"1987","title":"Proceedings of the Tenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1987","url":"https://ijcai.org/proceedings/1987/","year":1987,"location":"Milan, Italy","dates":"","editors":"John McDermott","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Cognitive Modeling","track":"Cognitive Modeling","number":29,"pages":{"first":151,"last":153},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}