Zur Startseite gehen
0,00 €*
Cover: 9781316519332 | The Principles of Deep Learning Theory | Daniel A. Roberts (u. a.)
Dekorationsartikel gehören nicht zum Leistungsumfang.
The Principles of Deep Learning Theory
Buch von Daniel A. Roberts (u. a.)
Sprache: Englisch

83,50 €*

inkl. MwSt.

Versandkostenfrei per Post / DHL

Aktuell nicht verfügbar

Kategorien:
Beschreibung
"This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning"--
"This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning"--
Über den Autor
Daniel A. Roberts was cofounder and CTO of Diffeo, an AI company acquired by Salesforce; a research scientist at Facebook AI Research; and a member of the School of Natural Sciences at the Institute for Advanced Study in Princeton, NJ. He was a Hertz Fellow, earning a PhD from MIT in theoretical physics, and was also a Marshall Scholar at Cambridge and Oxford Universities.
Inhaltsverzeichnis
Preface; 0. Initialization; 1. Pretraining; 2. Neural networks; 3. Effective theory of deep linear networks at initialization; 4. RG flow of preactivations; 5. Effective theory of preactivations at initializations; 6. Bayesian learning; 7. Gradient-based learning; 8. RG flow of the neural tangent kernel; 9. Effective theory of the NTK at initialization; 10. Kernel learning; 11. Representation learning; ¿. The end of training; ¿. Epilogue; A. Information in deep learning; B. Residual learning; References; Index.
Details
Erscheinungsjahr: 2022
Genre: Importe, Physik
Rubrik: Naturwissenschaften & Technik
Medium: Buch
Inhalt: Gebunden
ISBN-13: 9781316519332
ISBN-10: 1316519333
Sprache: Englisch
Ausstattung / Beilage: HC gerader Rücken kaschiert
Einband: Gebunden
Autor: Roberts, Daniel A.
Yaida, Sho
Hanin, Boris
Hersteller: Cambridge University Press
Verantwortliche Person für die EU: Produktsicherheitsverantwortliche/r, Europaallee 1, D-36244 Bad Hersfeld, gpsr@libri.de
Maße: 260 x 183 x 30 mm
Von/Mit: Daniel A. Roberts (u. a.)
Erscheinungsdatum: 15.04.2022
Gewicht: 1,075 kg
Artikel-ID: 120952167
Über den Autor
Daniel A. Roberts was cofounder and CTO of Diffeo, an AI company acquired by Salesforce; a research scientist at Facebook AI Research; and a member of the School of Natural Sciences at the Institute for Advanced Study in Princeton, NJ. He was a Hertz Fellow, earning a PhD from MIT in theoretical physics, and was also a Marshall Scholar at Cambridge and Oxford Universities.
Inhaltsverzeichnis
Preface; 0. Initialization; 1. Pretraining; 2. Neural networks; 3. Effective theory of deep linear networks at initialization; 4. RG flow of preactivations; 5. Effective theory of preactivations at initializations; 6. Bayesian learning; 7. Gradient-based learning; 8. RG flow of the neural tangent kernel; 9. Effective theory of the NTK at initialization; 10. Kernel learning; 11. Representation learning; ¿. The end of training; ¿. Epilogue; A. Information in deep learning; B. Residual learning; References; Index.
Details
Erscheinungsjahr: 2022
Genre: Importe, Physik
Rubrik: Naturwissenschaften & Technik
Medium: Buch
Inhalt: Gebunden
ISBN-13: 9781316519332
ISBN-10: 1316519333
Sprache: Englisch
Ausstattung / Beilage: HC gerader Rücken kaschiert
Einband: Gebunden
Autor: Roberts, Daniel A.
Yaida, Sho
Hanin, Boris
Hersteller: Cambridge University Press
Verantwortliche Person für die EU: Produktsicherheitsverantwortliche/r, Europaallee 1, D-36244 Bad Hersfeld, gpsr@libri.de
Maße: 260 x 183 x 30 mm
Von/Mit: Daniel A. Roberts (u. a.)
Erscheinungsdatum: 15.04.2022
Gewicht: 1,075 kg
Artikel-ID: 120952167
Sicherheitshinweis

Ähnliche Produkte

Ähnliche Produkte

Taschenbuch
Cover: 9780226288628 | Mathematical Physics | Robert Geroch | Taschenbuch | Englisch | 1985
Mathematical Physics
EAN: 9780226288628
Sprache: Englisch
Von/Mit: Robert Geroch

55,95 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9783446251502 | Aufbau der Physik | Carl Friedrich von Weizsäcker | Buch | Hanser
Aufbau der Physik
EAN: 9783446251502
Sprache: Deutsch
Von/Mit: Carl Friedrich von Weizsäcker

24,90 €*

Lieferzeit 2-3 Wochen

Buch
Cover: 9783540413783 | Bohmsche Mechanik als Grundlage der Quantenmechanik | Detlef Dürr | XV
Bohmsche Mechanik als Grundlage der Quantenmechanik
EAN: 9783540413783
Sprache: Deutsch
Von/Mit: Detlef Dürr

69,99 €*

Lieferzeit 2-3 Wochen

Taschenbuch
Cover: 9789814578585 | QUANTUM MECHANICS | A MODERN DEVELOPMENT (2ND EDITION) | Ballentine
QUANTUM MECHANICS (2ND ED)
EAN: 9789814578585
Sprache: Englisch
Von/Mit: Leslie E Ballentine

85,20 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9783960091189 | Natural Language Processing mit PyTorch | Delip Rao (u. a.) | Buch
Natural Language Processing mit PyTorch
Intelligente Sprachanwendungen mit Deep Learning erstellen
EAN: 9783960091189
Sprache: Deutsch
Von/Mit: Delip Rao (u. a.)

36,90 €*

Lieferzeit 2-4 Werktage

Taschenbuch
Cover: 9783658302108 | Künstliche Intelligenz | Gerhard Paaß (u. a.) | Taschenbuch | Deutsch
Künstliche Intelligenz
Was steckt hinter der Technologie der Zukunft?
EAN: 9783658302108
Sprache: Deutsch
Von/Mit: Gerhard Paaß (u. a.)

49,99 €*

Lieferzeit 2-4 Werktage

Taschenbuch
Cover: 9780367693923 | Explanatory Model Analysis | Przemyslaw Biecek (u. a.) | Taschenbuch
Explanatory Model Analysis
Explore, Explain, and Examine Predictive Models
EAN: 9780367693923
Sprache: Englisch
Von/Mit: Przemyslaw Biecek (u. a.)

69,20 €*

Lieferzeit 1-2 Wochen

Buch
Cover: 9783527414154 | Grundlagen kontinuierlicher Symmetrien | Franck Laloe | Buch | XII
Grundlagen kontinuierlicher Symmetrien
Von der Raumzeit zur Quantenmechanik
EAN: 9783527414154
Sprache: Deutsch
Von/Mit: Franck Laloe

65,00 €*

Lieferzeit 2-4 Werktage

Taschenbuch
Cover: 9783384176226 | Data Science und AI | Michael Oettinger | Taschenbuch | Deutsch
Data Science und AI
Eine praxisorientierte Einführung im Umfeld von Machine Learning, künstlicher Intelligenz und Big Data - 3....
EAN: 9783384176226
Sprache: Deutsch
Von/Mit: Michael Oettinger

17,90 €*

Aktuell nicht verfügbar

Diese Website verwendet Cookies, um eine bestmögliche Erfahrung bieten zu können. Mehr Informationen ...