{"pk":31739,"title":"APECS: A Solution to the Sequential Learning Problem","subtitle":null,"abstract":"This paper contains some modifications to Back\nPropagation that aim to remove one of its failings\nwithout sacrificing power. Adaptively Parametrised\nError Correcting Systems ( APECS ) are shown not\nto suffer from the sequential learning problem, and\nto be capable of solving EOR , higher order parity,\nand negation problems. This opens the w a y to\ndevelopment of connectionist models of associative\nlearning and memory that do not suffer from\n\"catastrophic interference\", and may shed light on\nissues such as the episodic / semantic memory\ndistinction.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Submitted Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/5r23d9tp","frozenauthors":[{"first_name":"I.P.L.","middle_name":"","last_name":"MCLaren","name_suffix":"","institution":"University of Warwick","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1993-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/31739/galley/22807/download/"}]}