Print List Price:	CDN$ 91.95
Kindle Price:	CDN$ 87.35 Save CDN$ 4.60 (5%)
	includes free international wireless delivery via *Amazon Whispernet*

The Principles of Deep Learning Theory: An Effective Theory Approach to Understanding Neural Networks by [Daniel A. Roberts, Sho Yaida, Boris Hanin]

Follow the Authors

Daniel A. Roberts

Sho Yaida

The Principles of Deep Learning Theory: An Effective Theory Approach to Understanding Neural Networks [Print Replica] Kindle Edition

by Daniel A. Roberts (Author), Sho Yaida (Author), Boris Hanin (Contributor) Format: Kindle Edition

23 ratings

See all formats and editions

Amazon Price

New from

Used from

Kindle Edition

"Please retry"

$87.35

—

Hardcover

"Please retry"

$91.95

$109.14

Kindle Edition
$87.35 Read with Our Free App
Hardcover
$91.95

4 Used from $109.14 6 New from $91.95

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.

Product description

Review

'In the history of science and technology, the engineering artifact often comes first: the telescope, the steam engine, digital communication. The theory that explains its function and its limitations often appears later: the laws of refraction, thermodynamics, and information theory. With the emergence of deep learning, AI-powered engineering wonders have entered our lives ― but our theoretical understanding of the power and limits of deep learning is still partial. This is one of the first books devoted to the theory of deep learning, and lays out the methods and results from recent theoretical approaches in a coherent manner.' Yann LeCun, New York University and Chief AI Scientist at Meta

'For a physicist, it is very interesting to see deep learning approached from the point of view of statistical physics. This book provides a fascinating perspective on a topic of increasing importance in the modern world.' Edward Witten, Institute for Advanced Study

'This is an important book that contributes big, unexpected new ideas for unraveling the mystery of deep learning’s effectiveness, in unusually clear prose. I hope it will be read and debated by experts in all the relevant disciplines.' Scott Aaronson, University of Texas at Austin

'It is not an exaggeration to say that the world is being revolutionized by deep learning methods for AI. But why do these deep networks work? This book offers an approach to this problem through the sophisticated tools of statistical physics and the renormalization group. The authors provide an elegant guided tour of these methods, interesting for experts and non-experts alike. They write with clarity and even moments of humor. Their results, many presented here for the first time, are the first steps in what promises to be a rich research program, combining theoretical depth with practical consequences.' William Bialek, Princeton University

'This book’s physics-trained authors have made a cool discovery, that feature learning depends critically on the ratio of depth to width in the neural net.' Gilbert Strang, Massachusetts Institute of Technology --This text refers to the hardcover edition.

Book Description

This volume develops an effective theory approach to understanding deep neural networks of practical relevance. --This text refers to the hardcover edition.

Product details

ASIN ‏ : ‎ B09YM1R6XW
Publisher ‏ : ‎ Cambridge University Press (May 26 2022)
Language ‏ : ‎ English
File size ‏ : ‎ 13154 KB
Simultaneous device usage ‏ : ‎ Up to 4 simultaneous devices, per publisher limits
Text-to-Speech ‏ : ‎ Not enabled
Enhanced typesetting ‏ : ‎ Not Enabled
X-Ray ‏ : ‎ Not Enabled
Word Wise ‏ : ‎ Not Enabled
Sticky notes ‏ : ‎ Not Enabled

Best Sellers Rank: #694,390 in Kindle Store (See Top 100 in Kindle Store)
- #78 in Mathematical Physics (Kindle Store)
- #78 in Mathematical Physics eBooks
- #430 in Mathematical Physics Books

Customer Reviews:
23 ratings

About the authors

Follow authors to get new release updates, plus improved recommendations.

Daniel A. Roberts
Brief content visible, double tap to read full content.
Full content visible, double tap to read brief content.
Dan Roberts (https://danintheory.com) is currently a Research Affiliate at the Center for Theoretical Physics at MIT, an Affiliate of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions, and a Principal Researcher at Salesforce. Previously, he was Co-Founder and CTO of Diffeo, a collaborative AI company acquired by Salesforce, a research scientist at Facebook AI Research (FAIR) in NYC, and a Member of the School of Natural Sciences at the Institute for Advanced Study in Princeton, NJ. Dan received a Ph.D. from MIT, funded by a Hertz Foundation Fellowship and the NDSEG, and he studied at Cambridge and Oxford as a Marshall Scholar. Dan's research has centered on the interplay between physics and computation, and previously he has focused on the relationship between black holes, quantum chaos, computational complexity, randomness, and how the laws of physics are related to fundamental limits of computation.
See more on the author's page
Sho Yaida
Brief content visible, double tap to read full content.
Full content visible, double tap to read brief content.
Sho Yaida (https://shoyaida.com) is currently a Research Scientist at Meta AI. Prior to joining Meta AI, he obtained his Ph.D. in physics at Stanford University -- where he studied physics of black holes and strongly correlated systems -- and held postdoctoral positions at MIT and at Duke University -- where he studied physics of glasses. At Meta AI, he studies physics of machine learning.
See more on the author's page

Kevin P. Murphy
104
Kindle Edition
1 offer from $127.99
Martin Kleppmann
4,554
Kindle Edition
1 offer from $54.99

Customer reviews

4.8 out of 5

23 global ratings

5 star		84%
4 star		10%
3 star		6%
2 star 0% (0%)		0%
1 star 0% (0%)		0%

How are ratings calculated?

Top reviews from other countries

Praveen Vaddadi

The job of a neural network is to listen to itself, because who else can it ask

Reviewed in India 🇮🇳 on December 23, 2022

Verified Purchase

Every neuron, every layer and every network is distrustful -- until you read this book.

Amazon Music Stream millions of songs	Amazon Advertising Find, attract, and engage customers	Amazon Business Everything for your business	Amazon Drive Cloud storage from Amazon	Amazon Web Services Scalable Cloud Computing Services

Book Depository Books With Free Delivery Worldwide	Goodreads Book reviews & recommendations	IMDb Movies, TV & Celebrities	Amazon Photos Unlimited Photo Storage Free With Prime	Shopbop Designer Fashion Brands

Warehouse Deals Open-Box Discounts	Whole Foods Market We Believe in Real Food	Amazon Renewed Like-new products you can trust	Blink Smart Security for Every Home