Picture 1 of 15

Stock photo

Understanding Deep Learning - Picture 1 of 15

Understanding Deep Learning - Picture 2 of 15

Understanding Deep Learning - Picture 3 of 15

Understanding Deep Learning - Picture 4 of 15

Understanding Deep Learning - Picture 5 of 15

Understanding Deep Learning - Picture 6 of 15

Understanding Deep Learning - Picture 7 of 15

Understanding Deep Learning - Picture 8 of 15

Understanding Deep Learning - Picture 9 of 15

Understanding Deep Learning - Picture 10 of 15

Understanding Deep Learning - Picture 11 of 15

Understanding Deep Learning - Picture 12 of 15

Understanding Deep Learning - Picture 13 of 15

Understanding Deep Learning - Picture 14 of 15

Understanding Deep Learning - Picture 15 of 15

Understanding Deep Learning by Simon J. D. Prince (2023, Hardcover)

5.01 product rating

ProflipUSA (2731)

99% positive feedback

Price:

US $83.27

ApproximatelyAU $127.64

+ $33.62 postage

Estimated delivery Mon, 25 Aug - Wed, 3 Sep

Returns:

30-day returns. Buyer pays for return postage. If you use an eBay postage label, it will be deducted from your refund amount.

Condition:

Brand new

Understanding Deep Learning

About this product

Product Identifiers

PublisherMIT Press

ISBN-100262048647

ISBN-139780262048644

eBay Product ID (ePID)21059341093

Product Key Features

Number of Pages544 Pages

Publication NameUnderstanding Deep Learning

LanguageEnglish

Publication Year2023

SubjectIntelligence (Ai) & Semantics, Neural Networks

TypeTextbook

AuthorSimon J. D. Prince

Subject AreaComputers

FormatHardcover

Dimensions

Item Height1.6 in

Item Weight47.3 Oz

Item Length9.3 in

Item Width8.3 in

Additional Product Features

Intended AudienceTrade

LCCN2023-034369

Dewey Edition23

IllustratedYes

Dewey Decimal006.31

Table Of ContentContents Preface xiii Acknowledgements xv 1 Introduction 1 2 Supervised learning 17 3 Shallow neural networks 25 4 Deep neural networks 41 5 Loss functions 56 6 Fitting models 77 7 Gradients and initialization 96 8 Measuring performance 118 9 Regularization 138 10 Convolutional networks 161 11 Residual networks 186 12 Transformers 207 13 Graph neural networks 240 14 Unsupervised learning 268 15 Generative Adversarial Networks 275 16 Normalizing flows 303 17 Variational autoencoders 326 18 Diffusion models 348 19 Reinforcement learning 373 20 Why does deep learning work? 401 21 Deep learning and ethics 420 A Notation 436 B Mathematics 439 C Probability 448 Bibliography 462 Index 513

SynopsisFrom machine learning basics to advanced models, this textbook curates the most important ideas and cutting-edge topics to provide a high density of critical information in an intuitive form. Covers current topics such as transformers and diffusion models, Presents challenging concepts in lay terms before dealing them in mathematical form and visual Illustration, Equips readers to implement naive versions of models, Offers a robust suite of instructor resources along with practice problems and programming exercises in Python Notebooks, Suitable for anyone with a basic background in applied mathematics, An authoritative, accessible, and up-to-date treatment of deep learning that strikes a pragmatic middle ground between theory and practice. Deep learning is a fast-moving field with sweeping relevance in today's increasingly digital world. Understanding Deep Learning provides an authoritative, accessible, and up-to-date treatment of the subject, covering all the key topics along with recent advances and cutting-edge concepts. Many deep learning texts are crowded with technical details that obscure fundamentals, but Simon Prince ruthlessly curates only the most important ideas to provide a high density of critical information in an intuitive and digestible form. From machine learning basics to advanced models, each concept is presented in lay terms and then detailed precisely in mathematical form and illustrated visually. The result is a lucid, self-contained textbook suitable for anyone with a basic background in applied mathematics. Up-to-date treatment of deep learning covers cutting-edge topics not found in existing texts, such as transformers and diffusion models Short, focused chapters progress in complexity, easing students into difficult concepts Pragmatic approach straddling theory and practice gives readers the level of detail required to implement naive versions of models Streamlined presentation separates critical ideas from background context and extraneous detail Minimal mathematical prerequisites, extensive illustrations, and practice problems make challenging material widely accessible Programming exercises offered in accompanying Python Notebooks

LC Classification NumberQ325.73.P75 2023