02631nam 22002897a 4500003000600000005001700006008004100023020001800064040001000082082002000092100002200112245014400134260005300278300003300331500003300364504005100397505021100448520112300659650003701782650005301819650001701872700001501889776015801904942001502062952024502077999001902322IIITD20240815020005.0240518b |||||||| |||| 00| 0 eng d a9781316519332 aIIITD00aCB 006.3bROB-P1 aRoberts, Daniel A14aThe principles of deep learning theory :ban effective theory approach to understanding neural networkscby Daniel A. Roberts and Sho Yaida aNew York :bCambridge University Press, cÃ2022 ax, 460 p. :bill ; c26 cm. aThis book include an index. aIncludes bibliographical references and index. tPretraining tNeural network teffective theory of deep linear networks at initializationtRG flow of presentationsteffective theory of the NTK at initializationtKernel learning trepresentation learning a"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"-- 0aDeep learning (Machine learning) 7aSCIENCE / Physics / Mathematical & Computational 7aPretraining aYaida, Sho08iOnline version:aRoberts, Daniel A.tPrinciples of deep learning theoryb1.dNew York : Cambridge University Press, 2022z9781009023405w(DLC) 2021060636 2ddccBK01 00102ddc40708CSEaIIITbIIITcREFd2024-05-18g4266.15l1m1oCB 006.3 ROB-Pp012958r2024-09-13s2024-08-14v¹ 59.99w2024-05-18yBKzDBT Project GranteTB439f2024-03-30jEmail-29-03-2024k2024-03-29xTechnical Bureau India Pvt. Ltd. c172601d172601