Détail d'une collection
|
|
Documents disponibles dans la collection
trié(s) par (Pertinence décroissant(e), Titre croissant(e)) Affiner la recherche
Titre : Deep learning Type de document : texte imprimé Auteurs : Ian J. Goodfellow (1987-....), Auteur ; Yoshua Bengio (1964-....), Auteur ; Aaron C. Courville Editeur : Cambridge, Mass. : MIT Press Année de publication : 2016, cop. 2016 Collection : Adaptive computation and machine learning Importance : 1 vol. (XXII-775 p.) Présentation : ill. en noir et en coul., graph., couv. ill. en coul. Format : 24 cm ISBN/ISSN/EAN : 978-0-262-03561-3 Note générale : PPN 197682979 Langues : Anglais (eng) Tags : Apprentissage automatique Apprentissage profond Modèles mathématiques Intelligence artificielle Analyse multivariée Probabilités Information, Théorie de l' Monte-Carlo, Méthode de Machine learning Mathematical models Artificial intelligence Multivariate analysis Information theory Probabilities Monte Carlo methods Index. décimale : 006.31 Apprentissage automatique (informatique) Résumé : Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones ; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. (4e de couverture) Note de contenu : Bibliographie p. [711]-766. - Index p.[767]-775
Sommaire (abrégé) : I- Applied math and machine learning basics (p.27) - 2. Linear algebra (p.29) - 3. Probability and information theory (p.51) - 4. Numerical computation (p.77) - 5. Machine learning basics (p.95) -- II - Deep networks : modern practices (p.161) -- 6. Deep feedforward networks (p.163) - 7. Regularization for deep learning (p.221) -- 8. Optimization for training deep models (p.267) - 9. Convolutional networks (p.321) - 10. Sequence modeling : recurrent and recursive nets (p.363) - 11. Practical methodology (p.409) -- 12. Applications (p.431) -- III- Deep learning research (p.475) - 13. Linear factor models (p.479) - 14. Autoencoders (p.493)- 15. Representation learning (p.517) - 16. Structured probabilistic models for deep learning (p.549) - 17. Monte Carlo methods (p.581) -- 18. Confronting the partition function (p.597) - 19. Approximate inference (p.623) - 20. Deep generative models (p.645) -- Bibliography (p.711-766) -- Index (p.767-775)Deep learning [texte imprimé] / Ian J. Goodfellow (1987-....), Auteur ; Yoshua Bengio (1964-....), Auteur ; Aaron C. Courville . - Cambridge, Mass. : MIT Press, 2016, cop. 2016 . - 1 vol. (XXII-775 p.) : ill. en noir et en coul., graph., couv. ill. en coul. ; 24 cm. - (Adaptive computation and machine learning) .
ISBN : 978-0-262-03561-3
PPN 197682979
Langues : Anglais (eng)
Tags : Apprentissage automatique Apprentissage profond Modèles mathématiques Intelligence artificielle Analyse multivariée Probabilités Information, Théorie de l' Monte-Carlo, Méthode de Machine learning Mathematical models Artificial intelligence Multivariate analysis Information theory Probabilities Monte Carlo methods Index. décimale : 006.31 Apprentissage automatique (informatique) Résumé : Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones ; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. (4e de couverture) Note de contenu : Bibliographie p. [711]-766. - Index p.[767]-775
Sommaire (abrégé) : I- Applied math and machine learning basics (p.27) - 2. Linear algebra (p.29) - 3. Probability and information theory (p.51) - 4. Numerical computation (p.77) - 5. Machine learning basics (p.95) -- II - Deep networks : modern practices (p.161) -- 6. Deep feedforward networks (p.163) - 7. Regularization for deep learning (p.221) -- 8. Optimization for training deep models (p.267) - 9. Convolutional networks (p.321) - 10. Sequence modeling : recurrent and recursive nets (p.363) - 11. Practical methodology (p.409) -- 12. Applications (p.431) -- III- Deep learning research (p.475) - 13. Linear factor models (p.479) - 14. Autoencoders (p.493)- 15. Representation learning (p.517) - 16. Structured probabilistic models for deep learning (p.549) - 17. Monte Carlo methods (p.581) -- 18. Confronting the partition function (p.597) - 19. Approximate inference (p.623) - 20. Deep generative models (p.645) -- Bibliography (p.711-766) -- Index (p.767-775)Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité OCA-NI-011181 011181 Ouvrages / Books OCA Bib. Nice Mont-Gros NI-Salle de lecture-Ouvrages Sorti jusqu'au 25/02/2026
Titre : Gaussian Processes for Machine Learning Type de document : texte imprimé Auteurs : Carl Edward Rasmussen (1969-....), Auteur ; Christopher K. I. Williams, Auteur Editeur : Cambridge, Mass. : MIT Press Année de publication : 2006, cop. 2006 Collection : Adaptive computation and machine learning Importance : 1 vol. (XVIII-248 p.) Présentation : graphiques, figures, illustrations, jaquette illustrée Format : 26 cm ISBN/ISSN/EAN : 978-0-262-18253-9 Note générale : PPN 097588938 .- ISBN 0-262-18253-X (rel.) Document accessible en ligne sur Mit Press direct (https://direct.mit.edu/books/oa-monograph/2320/Gaussian-Processes-for-Machine-Learning ; https://gaussianprocess.org/gpml/chapters/RW.pdf) Langues : Anglais (eng) Tags : Processus gaussiens -- Informatique Apprentissage automatique -- Modèles mathématiques Markov, Processus de Gaussian processes -- Data processing Machine learning -- Mathematical models Markov processes Index. décimale : 519.23 Processus probabilistes - Processus stochastiques - Processus gaussiens Résumé : Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes. Note de contenu : Bibliographie p. [223]-238. Index auteurs p.[239]-243. Index sujet p.[244]-248 En ligne : https://direct.mit.edu/books/oa-monograph/2320/Gaussian-Processes-for-Machine-Le [...] Gaussian Processes for Machine Learning [texte imprimé] / Carl Edward Rasmussen (1969-....), Auteur ; Christopher K. I. Williams, Auteur . - Cambridge, Mass. : MIT Press, 2006, cop. 2006 . - 1 vol. (XVIII-248 p.) : graphiques, figures, illustrations, jaquette illustrée ; 26 cm. - (Adaptive computation and machine learning) .
ISBN : 978-0-262-18253-9
PPN 097588938 .- ISBN 0-262-18253-X (rel.) Document accessible en ligne sur Mit Press direct (https://direct.mit.edu/books/oa-monograph/2320/Gaussian-Processes-for-Machine-Learning ; https://gaussianprocess.org/gpml/chapters/RW.pdf)
Langues : Anglais (eng)
Tags : Processus gaussiens -- Informatique Apprentissage automatique -- Modèles mathématiques Markov, Processus de Gaussian processes -- Data processing Machine learning -- Mathematical models Markov processes Index. décimale : 519.23 Processus probabilistes - Processus stochastiques - Processus gaussiens Résumé : Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes. Note de contenu : Bibliographie p. [223]-238. Index auteurs p.[239]-243. Index sujet p.[244]-248 En ligne : https://direct.mit.edu/books/oa-monograph/2320/Gaussian-Processes-for-Machine-Le [...] Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité OCA-NI-011187 011187 Ouvrages / Books OCA Bib. Nice Mont-Gros NI-Salle de lecture-Ouvrages Sorti jusqu'au 09/04/2026
