000			01880 a2200253 4500
003			OSt
005			20241125170846.0
008			241125b xxu||||| |||| 00| 0 eng d
020			_a9781316519332
040			_cIIT Kanpur
041			_aeng
082			_a006.31 _bR541p
100			_aRoberts, Daniel A
245			_aPrinciples of deep learning theory _ban effective theory approach to understanding neural networks _cDaniel A. Roberts and Sho Yaida
260			_bCambridge University Press _c2022 _aCambridge
300			_ax, 460p
500			_abased on research in collaboration with Boris Hanin
520			_aThis 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
650			_aDeep learning
650			_aMachine learning
650			_aMathematical & Computational
700			_aYaida, Sho
942			_cBK
999			_c567271 _d567271