{"pk":30562,"title":"Using Fast Weights to Deblur Old Memories","subtitle":null,"abstract":"Connectionist models usually have a single weight on each connection. Some interesting newproperties emerge if each connection has two weights: A slowly changing, plastic weight which stores long-term knowledge and a fast-changing, elastic weight which stores temporary knowledge and spontaneously decays towards zero. If a network learns a set of associations and then these associationsare \"blurred\" by subsequent learning, all the original associations can be \"deblurred\" by rehearsing on just a few of them. The rehearsal allows the fast weights to take on values that temporarily cancel outthe changes in the slow weights caused by the subsequent learning.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Connectionism I","is_remote":true,"remote_url":"https://escholarship.org/uc/item/0570j1dp","frozenauthors":[{"first_name":"Geoffrey","middle_name":"E.","last_name":"Hinton","name_suffix":"","institution":"Carnegie-Mellon University","department":""},{"first_name":"David","middle_name":"C.","last_name":"Plaut","name_suffix":"","institution":"Carnegie-Mellon University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1987-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/30562/galley/20411/download/"}]}