Amazon cover image
Image from Amazon.com

The principles of deep learning theory : an effective theory approach to understanding neural networks

By: Contributor(s): Material type: TextTextPublication details: New York : Cambridge University Press, ©2022Description: x, 460 p. : ill ; 26 cmISBN:
  • 9781316519332
Subject(s): Additional physical formats: Online version:: Principles of deep learning theoryDDC classification:
  • CB 006.3 ROB-P
Contents:
Pretraining Neural network effective theory of deep linear networks at initialization RG flow of presentations effective theory of the NTK at initialization Kernel learning representation learning
Summary: "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"--
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Collection Call number Status Notes Date due Barcode Item holds
Books Books IIITD Reference Computer Science and Engineering CB 006.3 ROB-P (Browse shelf(Opens below)) Available DBT Project Grant 012958
Total holds: 0

This book include an index.

Includes bibliographical references and index.

Pretraining Neural network effective theory of deep linear networks at initialization RG flow of presentations effective theory of the NTK at initialization Kernel learning representation 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"--

There are no comments on this title.

to post a comment.
© 2024 IIIT-Delhi, library@iiitd.ac.in