This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
Da: Better World Books Ltd, Dunfermline, Regno Unito
Condizione: Good. 1986th Edition. Former library copy. Pages intact with minimal writing/highlighting. The binding may be loose and creased. Dust jackets/supplements are not included. Includes library markings. Stock photo provided. Product includes identifying sticker. Better World Books: Buy Books. Do Good. Codice articolo 10202404-6
Quantità: 1 disponibili
Da: GreatBookPrices, Columbia, MD, U.S.A.
Condizione: As New. Unread book in perfect condition. Codice articolo 2073551
Quantità: 15 disponibili
Da: moluna, Greven, Germania
Gebunden. Condizione: New. Codice articolo 5982389
Quantità: Più di 20 disponibili
Da: Ria Christie Collections, Uxbridge, Regno Unito
Condizione: New. In English. Codice articolo ria9780898382235_new
Quantità: Più di 20 disponibili
Da: GreatBookPrices, Columbia, MD, U.S.A.
Condizione: New. Codice articolo 2073551-n
Quantità: 15 disponibili
Da: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germania
Buch. Condizione: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -This book is based on the author's Ph.D. dissertation. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias. 188 pp. Englisch. Codice articolo 9780898382235
Quantità: 2 disponibili
Da: AHA-BUCH GmbH, Einbeck, Germania
Buch. Condizione: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - This book is based on the author's Ph.D. dissertation. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias. Codice articolo 9780898382235
Quantità: 1 disponibili
Da: Books Puddle, Woodside, NY, U.S.A.
Condizione: New. pp. 188. Codice articolo 263099922
Quantità: 4 disponibili
Da: buchversandmimpf2000, Emtmannsberg, BAYE, Germania
Buch. Condizione: Neu. This item is printed on demand - Print on Demand Titel. Neuware -This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.Springer-Verlag KG, Sachsenplatz 4-6, 1201 Wien 188 pp. Englisch. Codice articolo 9780898382235
Quantità: 1 disponibili
Da: Majestic Books, Hounslow, Regno Unito
Condizione: New. Print on Demand pp. 188 52:B&W 6.14 x 9.21in or 234 x 156mm (Royal 8vo) Case Laminate on White w/Gloss Lam. Codice articolo 5829325
Quantità: 4 disponibili