Risto Miikkulainen draws on recent connectionist work in language comprehension to create a model that can understand natural language. Using the DISCERN system as an example, he describes a general approach to building high-level cognitive models from distributed neural networks and shows how the special properties of such networks are useful in modeling human performance. In this approach connectionist networks are not only plausible models of isolated cognitive phenomena, but also sufficient constituents for complete artificial intelligence systems. Distributed neural networks have been very successful in modeling isolated cognitive phenomena, but complex high-level behavior has been tractable only with symbolic artificial intelligence techniques. Aiming to bridge this gap, Miikkulainen describes DISCERN, a complete natural language processing system implemented entirely at the subsymbolic level. In DISCERN, distributed neural network models of parsing, generating, reasoning, lexical processing, and episodic memory are integrated into a single system that learns to read, paraphrase, and answer questions about stereotypical narratives. Miikkulainen's work, which includes a comprehensive survey of the connectionist literature related to natural language processing, will prove especially valuable to researchers interested in practical techniques for high-level representation, inferencing, memory modeling, and modular connectionist architectures.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
Risto Miikkulainen is an Assistant Professor in the Department of Computer Sciences at The University of Texas at Austin.
Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.
EUR 8,95 expédition depuis Allemagne vers France
Destinations, frais et délaisEUR 39,69 expédition depuis Etats-Unis vers France
Destinations, frais et délaisVendeur : books4less (Versandantiquariat Petra Gros GmbH & Co. KG), Welling, Allemagne
gebundene Ausgabe. Etat : Gut. 391 Seiten Der Erhaltungszustand des hier angebotenen Werks ist trotz seiner Bibliotheksnutzung sehr sauber und kann entsprechende Merkmale aufweisen (Rückenschild, Instituts-Stempel.). In ENGLISCHER Sprache. Sprache: Englisch Gewicht in Gramm: 780. N° de réf. du vendeur 2151881
Quantité disponible : 1 disponible(s)
Vendeur : Gerald Wollermann, Bad Vilbel, Allemagne
Etat : Gut. New ed. 403 Seiten Besitzereintrag innen. Schutzumschlag etwas lädiert. Gebrauchsspuren. Innerhalb Deutschlands Versand je nach Größe/Gewicht als Großbrief bzw. Bücher- und Warensendung mit der Post oder per DHL. Rechnung mit MwSt.-Ausweis liegt jeder Lieferung bei. Sprache: Englisch Gewicht in Gramm: 831 Gebundene Ausgabe, Größe: 16 x 3.7 x 23.1 cm. N° de réf. du vendeur 939817
Quantité disponible : 1 disponible(s)
Vendeur : Cotswold Internet Books, Cheltenham, Royaume-Uni
Etat : Used - Good. First Edition. Text VG - bright & clean in tight binding; dust jacket rather worn, with loss to back panel. N° de réf. du vendeur BOOKS262541I
Quantité disponible : 1 disponible(s)
Vendeur : G3 Books, Winnipeg, MB, Canada
Hardcover. Etat : Very Good. 391 Pages. Unread and Unmarked. n. N° de réf. du vendeur 003453
Quantité disponible : 1 disponible(s)
Vendeur : Kloof Booksellers & Scientia Verlag, Amsterdam, Pays-Bas
Etat : as new. Cambridge, MA: The MIT Press, 1993. Hardcover. Dustjacket. 403 pp.- Risto Miikkulainen draws on recent connectionist work in language comprehension to create a model that can understand natural language. Using the DISCERN system as an example, he describes a general approach to building high-level cognitive models from distributed neural networks and shows how the special properties of such networks are useful in modeling human performance. In this approach connectionist networks are not only plausible models of isolated cognitive phenomena, but also sufficient constituents for complete artificial intelligence systems.Distributed neural networks have been very successful in modeling isolated cognitive phenomena, but complex high-level behavior has been tractable only with symbolic artificial intelligence techniques. Aiming to bridge this gap, Miikkulainen describes DISCERN, a complete natural language processing system implemented entirely at the subsymbolic level. In DISCERN, distributed neural network models of parsing, generating, reasoning, lexical processing, and episodic memory are integrated into a single system that learns to read, paraphrase, and answer questions about stereotypical narratives.Miikkulainen's work, which includes a comprehensive survey of the connectionist literature related to natural language processing, will prove especially valuable to researchers interested in practical techniques for high-level representation, inferencing, memory modeling, and modular connectionist architectures. English text. Condition : as new. Condition : as new copy. ISBN 9780262132909. Keywords : , Neural networks. N° de réf. du vendeur 262870
Quantité disponible : 1 disponible(s)
Vendeur : Grey Matter Books, Hadley, MA, Etats-Unis
Hardcover. Etat : Very Good. Etat de la jaquette : Very Good. Text is unmarked; pages are bright. Binding is tight and square. Dust jacket shows some light edgewear. 391pp. N° de réf. du vendeur 059714
Quantité disponible : 1 disponible(s)
Vendeur : Ammareal, Morangis, France
Hardcover. Etat : Bon. Ancien livre de bibliothèque. Couverture différente. Edition 1993. Ammareal reverse jusqu'à 15% du prix net de cet article à des organisations caritatives. ENGLISH DESCRIPTION Book Condition: Used, Good. Former library book. Different cover. Edition 1993. Ammareal gives back up to 15% of this item's net price to charity organizations. N° de réf. du vendeur E-521-561
Quantité disponible : 1 disponible(s)
Vendeur : The Book Spot, Sioux Falls, MN, Etats-Unis
Hardcover. Etat : New. N° de réf. du vendeur Abebooks10554
Quantité disponible : 1 disponible(s)
Vendeur : dsmbooks, Liverpool, Royaume-Uni
Hardcover. Etat : Good. Good. book. N° de réf. du vendeur D8S0-3-M-0262132907-3
Quantité disponible : 1 disponible(s)