{"type":"ScholarlyArticle","title":"Dynamic Conflict Resolution in a Connectionist Rule-Based System","authors":[{"name":"Clayton McMillan","slug":"clayton-mcmillan","given":"Clayton","family":"McMillan","affiliation":""},{"name":"Michael Mozer","slug":"michael-mozer","given":"Michael","family":"Mozer","affiliation":""},{"name":"Paul Smolensky","slug":"paul-smolensky","given":"Paul","family":"Smolensky","affiliation":""}],"abstract":"In performing higher level cognitive tasks in a connectionist network, we have argued that it is useful to incorporate symbol processing formalisms and mechanisms directly into the network architecture. We have previously described a neural network, RuleNet [McMillan et al., 1992] that maps strings of input symbols to strings of output symbOls. RuleNet discovers a functional categorization of the input symbols, as well as a compact set of symbolic rules that operate on these categories to generate the output strings. The integration of subsymbolic categorization and symbolic rule following in a single system yields a variety of important consequences. This paper explores one consequence in detail, namely a novel way in which RuleNet performs conflict resolution among rules: When a conflict arises, RuleNet exploits the varying category membership strengths of input symbols to select a rule. This dynamic, content-based conflict resolution technique contrasts with traditional, broad heuristic techniques such as selection of the most specific or least recently used rule. RuleNet also has the ability to learn a priority ranking of rules, and this ranking can interact with the category-strength selection technique in a uniform quantitative framework. This uniform framework-the combination of evidence in a connectionist system-is a powerful and elegant approach to conflict resolution.","doi":null,"url":"https://ijcai.org/proceedings/1993/189","pdf":"https://ijcai.org/proceedings/1993/0189.pdf","markdown":"https://ijcai.org/proceedings/1993/189.md","bibtex":"https://ijcai.org/proceedings/1993/bibtex/189","volume":{"slug":"1993","title":"Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1993","url":"https://ijcai.org/proceedings/1993/","year":1993,"location":"Chambéry, France","dates":"","editors":"Ruzena Bajcsy","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Neural Networks","track":"Neural Networks","number":189,"pages":{"first":1366,"last":1372},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}