000 | 02374nam a22002777a 4500 | ||
---|---|---|---|
003 | IIITD | ||
005 | 20240815020005.0 | ||
008 | 240518b |||||||| |||| 00| 0 eng d | ||
020 | _a9781316519332 | ||
040 | _aIIITD | ||
082 | 0 | 0 |
_aCB 006.3 _bROB-P |
100 | 1 | _aRoberts, Daniel A | |
245 | 1 | 4 |
_aThe principles of deep learning theory : _ban effective theory approach to understanding neural networks _cby Daniel A. Roberts and Sho Yaida |
260 |
_aNew York : _bCambridge University Press, _c©2022 |
||
300 |
_ax, 460 p. : _bill ; _c26 cm. |
||
500 | _aThis book include an index. | ||
504 | _aIncludes bibliographical references and index. | ||
505 |
_tPretraining _tNeural network _teffective theory of deep linear networks at initialization _tRG flow of presentations _teffective theory of the NTK at initialization _tKernel learning _trepresentation learning |
||
520 | _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"-- | ||
650 | 0 | _aDeep learning (Machine learning) | |
650 | 7 | _aSCIENCE / Physics / Mathematical & Computational | |
650 | 7 | _aPretraining | |
700 | _aYaida, Sho | ||
776 | 0 | 8 |
_iOnline version: _aRoberts, Daniel A. _tPrinciples of deep learning theory _b1. _dNew York : Cambridge University Press, 2022 _z9781009023405 _w(DLC) 2021060636 |
942 |
_2ddc _cBK _01 |
||
999 |
_c172601 _d172601 |