The principles of deep learning theory: an effective theory approach to understanding neural networks
"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 res...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Weitere Verfasser: | |
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Cambridge, United Kingdom
Cambridge University Press
2022
|
| Schlagworte: | |
| Zusammenfassung: | "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"-- |
| Beschreibung: | Includes bibliographical references and index |
| Beschreibung: | x, 460 Seiten Diagramme |
| ISBN: | 9781316519332 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV048404365 | ||
| 003 | DE-604 | ||
| 005 | 20221201 | ||
| 007 | t | ||
| 008 | 220811s2022 xxu|||| |||| 00||| eng d | ||
| 020 | |a 9781316519332 |c hardback |9 978-1-316-51933-2 | ||
| 024 | 3 | |a 9781316519332 | |
| 035 | |a (OCoLC)1319077261 | ||
| 035 | |a (DE-599)KXP1793559562 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 044 | |a xxu |c XD-US | ||
| 049 | |a DE-83 |a DE-91G |a DE-20 | ||
| 082 | 0 | |a 006.3/1 | |
| 084 | |a 54.72 |2 bkl | ||
| 084 | |a DAT 708 |2 stub | ||
| 084 | |a DAT 717 |2 stub | ||
| 084 | |a DAT 700 |2 stub | ||
| 084 | |a 68T05 |2 msc | ||
| 084 | |a 68T07 |2 msc | ||
| 100 | 1 | |a Roberts, Daniel A. |d 1987- |0 (DE-588)1261776224 |4 aut | |
| 245 | 1 | 0 | |a The principles of deep learning theory |b an effective theory approach to understanding neural networks |c Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University |
| 264 | 1 | |a Cambridge, United Kingdom |b Cambridge University Press |c 2022 | |
| 264 | 4 | |c © 2022 | |
| 300 | |a x, 460 Seiten |b Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Includes bibliographical references and index | ||
| 520 | 3 | |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 | 7 | |a Deep learning |0 (DE-588)1135597375 |2 gnd |9 rswk-swf |
| 653 | 0 | |a Deep learning (Machine learning) | |
| 653 | 0 | |a SCIENCE / Physics / Mathematical & Computational | |
| 689 | 0 | 0 | |a Deep learning |0 (DE-588)1135597375 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Yaida, Sho |0 (DE-588)1261764668 |4 aut | |
| 700 | 1 | |a Hanin, Boris |d ca. 20./21. Jh. |0 (DE-588)1261776534 |4 ctb | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe, EPUB |z 978-1-00-902340-5 |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-033782879 | ||
Datensatz im Suchindex
| _version_ | 1804184302249836544 |
|---|---|
| adam_txt | |
| any_adam_object | |
| any_adam_object_boolean | |
| author | Roberts, Daniel A. 1987- Yaida, Sho |
| author2 | Hanin, Boris ca. 20./21. Jh |
| author2_role | ctb |
| author2_variant | b h bh |
| author_GND | (DE-588)1261776224 (DE-588)1261764668 (DE-588)1261776534 |
| author_facet | Roberts, Daniel A. 1987- Yaida, Sho Hanin, Boris ca. 20./21. Jh |
| author_role | aut aut |
| author_sort | Roberts, Daniel A. 1987- |
| author_variant | d a r da dar s y sy |
| building | Verbundindex |
| bvnumber | BV048404365 |
| classification_tum | DAT 708 DAT 717 DAT 700 |
| ctrlnum | (OCoLC)1319077261 (DE-599)KXP1793559562 |
| dewey-full | 006.3/1 |
| dewey-hundreds | 000 - Computer science, information, general works |
| dewey-ones | 006 - Special computer methods |
| dewey-raw | 006.3/1 |
| dewey-search | 006.3/1 |
| dewey-sort | 16.3 11 |
| dewey-tens | 000 - Computer science, information, general works |
| discipline | Informatik |
| discipline_str_mv | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02884nam a2200493 c 4500</leader><controlfield tag="001">BV048404365</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20221201 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">220811s2022 xxu|||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781316519332</subfield><subfield code="c">hardback</subfield><subfield code="9">978-1-316-51933-2</subfield></datafield><datafield tag="024" ind1="3" ind2=" "><subfield code="a">9781316519332</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1319077261</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)KXP1793559562</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">xxu</subfield><subfield code="c">XD-US</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-83</subfield><subfield code="a">DE-91G</subfield><subfield code="a">DE-20</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">006.3/1</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 708</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 717</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 700</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">68T05</subfield><subfield code="2">msc</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">68T07</subfield><subfield code="2">msc</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Roberts, Daniel A.</subfield><subfield code="d">1987-</subfield><subfield code="0">(DE-588)1261776224</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">The principles of deep learning theory</subfield><subfield code="b">an effective theory approach to understanding neural networks</subfield><subfield code="c">Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge, United Kingdom</subfield><subfield code="b">Cambridge University Press</subfield><subfield code="c">2022</subfield></datafield><datafield tag="264" ind1=" " ind2="4"><subfield code="c">© 2022</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">x, 460 Seiten</subfield><subfield code="b">Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Includes bibliographical references and index</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="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"--</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Deep learning</subfield><subfield code="0">(DE-588)1135597375</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Deep learning (Machine learning)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">SCIENCE / Physics / Mathematical & Computational</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Deep learning</subfield><subfield code="0">(DE-588)1135597375</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yaida, Sho</subfield><subfield code="0">(DE-588)1261764668</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hanin, Boris</subfield><subfield code="d">ca. 20./21. Jh.</subfield><subfield code="0">(DE-588)1261776534</subfield><subfield code="4">ctb</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe, EPUB</subfield><subfield code="z">978-1-00-902340-5</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-033782879</subfield></datafield></record></collection> |
| id | DE-604.BV048404365 |
| illustrated | Not Illustrated |
| index_date | 2024-07-03T20:23:38Z |
| indexdate | 2024-07-10T09:37:11Z |
| institution | BVB |
| isbn | 9781316519332 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-033782879 |
| oclc_num | 1319077261 |
| open_access_boolean | |
| owner | DE-83 DE-91G DE-BY-TUM DE-20 |
| owner_facet | DE-83 DE-91G DE-BY-TUM DE-20 |
| physical | x, 460 Seiten Diagramme |
| publishDate | 2022 |
| publishDateSearch | 2022 |
| publishDateSort | 2022 |
| publisher | Cambridge University Press |
| record_format | marc |
| spelling | Roberts, Daniel A. 1987- (DE-588)1261776224 aut The principles of deep learning theory an effective theory approach to understanding neural networks Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University Cambridge, United Kingdom Cambridge University Press 2022 © 2022 x, 460 Seiten Diagramme txt rdacontent n rdamedia nc rdacarrier Includes bibliographical references and index "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"-- Deep learning (DE-588)1135597375 gnd rswk-swf Deep learning (Machine learning) SCIENCE / Physics / Mathematical & Computational Deep learning (DE-588)1135597375 s DE-604 Yaida, Sho (DE-588)1261764668 aut Hanin, Boris ca. 20./21. Jh. (DE-588)1261776534 ctb Erscheint auch als Online-Ausgabe, EPUB 978-1-00-902340-5 |
| spellingShingle | Roberts, Daniel A. 1987- Yaida, Sho The principles of deep learning theory an effective theory approach to understanding neural networks Deep learning (DE-588)1135597375 gnd |
| subject_GND | (DE-588)1135597375 |
| title | The principles of deep learning theory an effective theory approach to understanding neural networks |
| title_auth | The principles of deep learning theory an effective theory approach to understanding neural networks |
| title_exact_search | The principles of deep learning theory an effective theory approach to understanding neural networks |
| title_exact_search_txtP | The principles of deep learning theory an effective theory approach to understanding neural networks |
| title_full | The principles of deep learning theory an effective theory approach to understanding neural networks Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University |
| title_fullStr | The principles of deep learning theory an effective theory approach to understanding neural networks Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University |
| title_full_unstemmed | The principles of deep learning theory an effective theory approach to understanding neural networks Daniel A. Roberts: MIT ; Sho Yaida: Meta AI ; based on research in collaboration with Boris Hanin: Princeton University |
| title_short | The principles of deep learning theory |
| title_sort | the principles of deep learning theory an effective theory approach to understanding neural networks |
| title_sub | an effective theory approach to understanding neural networks |
| topic | Deep learning (DE-588)1135597375 gnd |
| topic_facet | Deep learning |
| work_keys_str_mv | AT robertsdaniela theprinciplesofdeeplearningtheoryaneffectivetheoryapproachtounderstandingneuralnetworks AT yaidasho theprinciplesofdeeplearningtheoryaneffectivetheoryapproachtounderstandingneuralnetworks AT haninboris theprinciplesofdeeplearningtheoryaneffectivetheoryapproachtounderstandingneuralnetworks |