{"pk":31808,"title":"Artificial Evolution of Syntactic Aptitude","subtitle":null,"abstract":"Populations of simple recurrent neural networks were subject to simulations of evolution where the selection criterion was the ability of a network to learn to recognize strings from context free grammars. After a number of generations, networks emerged that use the activation values of the units feeding their recurrent connections to represent the depth of embedding in a string. Networks inherited innate biases to accurately learn members of a class of related context-free grammars, and, while learning, passed through periods during which exposure to spurious input interfered with their subsequent ability to learn a grammar.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Refereed Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/9919k906","frozenauthors":[{"first_name":"John","middle_name":"","last_name":"Batali","name_suffix":"","institution":"University of California at San Diego","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1994-01-01T13:00:00-05:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/31808/galley/22876/download/"}]}