Documents disponibles écrits par cet auteur

Learning machines / Nils J. Nilsson

Public ISBD Titre : Learning machines : foundations of trainable pattern-classifying systems Type de document : texte imprimé Auteurs : Nils J. Nilsson, Auteur Editeur : New York : McGraw-Hill Année de publication : 1965 Collection : McGraw-Hill series in systems science Importance : XI,137 p. Présentation : ill. Format : 23 cm Note générale : Bibliogr. at the end of chapters. - Index Langues : Anglais (eng) Mots-clés : Intelligence  artificielle Artificial  intelligence Index. décimale : 004.8 Intelligence artificielle Résumé : This monograph presents some of the results of research in the new and exciting field of learning machines. A learning machine, broadly defined, is any device whose actions are influenced by past experiences. The present work deals specifically with the theory of a subclass of learning machines, those which can be trained to recognize patterns. Some well-known examples of trainable pattern-classifying systems are the perceptron and the madaline and minos networks. Note de contenu : Summary : 1. Trainable pattern classifiers. 2. Some important discriminant functions : their properties and their implementations. 3. Parametric training methods. 4. Some nonparametric training methods for machines. 5. Training theorems. 6. Layered machines. 7. Piecewise linear machines. Learning machines : foundations of trainable pattern-classifying systems [texte imprimé] / Nils J. Nilsson, Auteur . - McGraw-Hill, 1965 . - XI,137 p. : ill. ; 23 cm. - (McGraw-Hill series in systems science) . Bibliogr. at the end of chapters. - Index Langues : Anglais (eng) Mots-clés : Intelligence  artificielle Artificial  intelligence Index. décimale : 004.8 Intelligence artificielle Résumé : This monograph presents some of the results of research in the new and exciting field of learning machines. A learning machine, broadly defined, is any device whose actions are influenced by past experiences. The present work deals specifically with the theory of a subclass of learning machines, those which can be trained to recognize patterns. Some well-known examples of trainable pattern-classifying systems are the perceptron and the madaline and minos networks. Note de contenu : Summary : 1. Trainable pattern classifiers. 2. Some important discriminant functions : their properties and their implementations. 3. Parametric training methods. 4. Some nonparametric training methods for machines. 5. Training theorems. 6. Layered machines. 7. Piecewise linear machines.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
010596	004.8 NIL	Papier	Bibliothèque Centrale	Informatique	Disponible	Consultation sur place