{"pk":30922,"title":"Discovering Faithful 'Wickelfeature' Representations in a Connectionist Network","subtitle":null,"abstract":"challenging problem for connectionist models is the representation of varying-length sequences, e.g., the sequence of phonemes that compose a word. One representation that has been proposed involves encoding each sequence element with respect to its local context; this is known as a Wickelfeature representation. Handcrafted Wickelfeature representations suffer from a number of limitations, as pointed out by Pinker and Prince (1988). However, these limitations can be avoided if the representation is constructed with a priori knowledge of the set of possible sequences. This paper proposes a specialized connectionist network architecture and learning algorithm for the discovery of faithful Wickelfeature representations — ones that do not lose critical information about the sequence to be encoded. The architecture is applied to a simplified version of Rumclhart and McCleiland's (1986) verb past-tense model.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Paper Presentations -- Group 2: Language","is_remote":true,"remote_url":"https://escholarship.org/uc/item/8vd3n76q","frozenauthors":[{"first_name":"Michael","middle_name":"C.","last_name":"Mozer","name_suffix":"","institution":"University of Colorado","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1990-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/30922/galley/20771/download/"}]}