國立虎尾科技大學 |

Geometry of Deep Learning = A Signal Processing Perspective /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Geometry of Deep Learning/ by Jong Chul Ye.
其他題名:	A Signal Processing Perspective /
作者:	Ye, Jong Chul.
面頁冊數:	XVI, 330 p. 1 illus.online resource. :
Contained By:	Springer Nature eBook
標題:	Mathematical and Computational Biology. -
電子資源:	https://doi.org/10.1007/978-981-16-6046-7
ISBN:	9789811660467

Geometry of Deep Learning = A Signal Processing Perspective /
Ye, Jong Chul.

Geometry of Deep LearningA Signal Processing Perspective /[electronic resource] :by Jong Chul Ye. - 1st ed. 2022. - XVI, 330 p. 1 illus.online resource. - Mathematics in Industry,372198-3283 ;. - Mathematics in Industry,34.

Part I Basic Tools for Machine Learning: 1. Mathematical Preliminaries -- 2. Linear and Kernel Classifiers -- 3. Linear, Logistic, and Kernel Regression -- 4. Reproducing Kernel Hilbert Space, Representer Theorem -- Part II Building Blocks of Deep Learning: 5. Biological Neural Networks -- 6. Artificial Neural Networks and Backpropagation -- 7. Convolutional Neural Networks -- 8. Graph Neural Networks -- 9. Normalization and Attention -- Part III Advanced Topics in Deep Learning -- 10. Geometry of Deep Neural Networks -- 11. Deep Learning Optimization -- 12. Generalization Capability of Deep Learning -- 13. Generative Models and Unsupervised Learning -- Summary and Outlook -- Bibliography -- Index.

The focus of this book is on providing students with insights into geometry that can help them understand deep learning from a unified perspective. Rather than describing deep learning as an implementation technique, as is usually the case in many existing deep learning books, here, deep learning is explained as an ultimate form of signal processing techniques that can be imagined. To support this claim, an overview of classical kernel machine learning approaches is presented, and their advantages and limitations are explained. Following a detailed explanation of the basic building blocks of deep neural networks from a biological and algorithmic point of view, the latest tools such as attention, normalization, Transformer, BERT, GPT-3, and others are described. Here, too, the focus is on the fact that in these heuristic approaches, there is an important, beautiful geometric structure behind the intuition that enables a systematic understanding. A unified geometric analysis to understand the working mechanism of deep learning from high-dimensional geometry is offered. Then, different forms of generative models like GAN, VAE, normalizing flows, optimal transport, and so on are described from a unified geometric perspective, showing that they actually come from statistical distance-minimization problems. Because this book contains up-to-date information from both a practical and theoretical point of view, it can be used as an advanced deep learning textbook in universities or as a reference source for researchers interested in acquiring the latest deep learning algorithms and their underlying principles. In addition, the book has been prepared for a codeshare course for both engineering and mathematics students, thus much of the content is interdisciplinary and will appeal to students from both disciplines.

ISBN: 9789811660467

Standard No.: 10.1007/978-981-16-6046-7doiSubjects--Topical Terms:

786706
Mathematical and Computational Biology.

LC Class. No.: QA319-329.9

Dewey Class. No.: 515.7

Geometry of Deep Learning = A Signal Processing Perspective /
LDR:03945nam a22004095i 4500 001 1092332
003 DE-He213
005 20220429024830.0
007 cr nn 008mamaa
008 221228s2022 si | s |||| 0|eng d
020 $a 9789811660467 $9 978-981-16-6046-7
024 7 $a 10.1007/978-981-16-6046-7 $2 doi
035 $a 978-981-16-6046-7
050 4 $a QA319-329.9
072 7 $a PBKF $2 bicssc
072 7 $a MAT037000 $2 bisacsh
072 7 $a PBKF $2 thema
082 0 4 $a 515.7 $2 23
100 1 $a Ye, Jong Chul. $e editor. $1 https://orcid.org/0000-0001-9763-9609 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1297876
245 1 0 $a Geometry of Deep Learning $h [electronic resource] : $b A Signal Processing Perspective / $c by Jong Chul Ye.
250 $a 1st ed. 2022.
264 1 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2022.
300 $a XVI, 330 p. 1 illus. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Mathematics in Industry, $x 2198-3283 ; $v 37
505 0 $a Part I Basic Tools for Machine Learning: 1. Mathematical Preliminaries -- 2. Linear and Kernel Classifiers -- 3. Linear, Logistic, and Kernel Regression -- 4. Reproducing Kernel Hilbert Space, Representer Theorem -- Part II Building Blocks of Deep Learning: 5. Biological Neural Networks -- 6. Artificial Neural Networks and Backpropagation -- 7. Convolutional Neural Networks -- 8. Graph Neural Networks -- 9. Normalization and Attention -- Part III Advanced Topics in Deep Learning -- 10. Geometry of Deep Neural Networks -- 11. Deep Learning Optimization -- 12. Generalization Capability of Deep Learning -- 13. Generative Models and Unsupervised Learning -- Summary and Outlook -- Bibliography -- Index.
520 $a The focus of this book is on providing students with insights into geometry that can help them understand deep learning from a unified perspective. Rather than describing deep learning as an implementation technique, as is usually the case in many existing deep learning books, here, deep learning is explained as an ultimate form of signal processing techniques that can be imagined. To support this claim, an overview of classical kernel machine learning approaches is presented, and their advantages and limitations are explained. Following a detailed explanation of the basic building blocks of deep neural networks from a biological and algorithmic point of view, the latest tools such as attention, normalization, Transformer, BERT, GPT-3, and others are described. Here, too, the focus is on the fact that in these heuristic approaches, there is an important, beautiful geometric structure behind the intuition that enables a systematic understanding. A unified geometric analysis to understand the working mechanism of deep learning from high-dimensional geometry is offered. Then, different forms of generative models like GAN, VAE, normalizing flows, optimal transport, and so on are described from a unified geometric perspective, showing that they actually come from statistical distance-minimization problems. Because this book contains up-to-date information from both a practical and theoretical point of view, it can be used as an advanced deep learning textbook in universities or as a reference source for researchers interested in acquiring the latest deep learning algorithms and their underlying principles. In addition, the book has been prepared for a codeshare course for both engineering and mathematics students, thus much of the content is interdisciplinary and will appeal to students from both disciplines.
650 2 4 $a Mathematical and Computational Biology. $3 786706
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 884110
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Differential Geometry. $3 671118
650 1 4 $a Functional Analysis. $3 672166
650 0 $a Biomathematics. $3 527725
650 0 $a Neural networks (Computer science) . $3 1253765
650 0 $a Artificial intelligence. $3 559380
650 0 $a Geometry, Differential. $3 527830
650 0 $a Functional analysis. $3 527706
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9789811660450
776 0 8 $i Printed edition: $z 9789811660474
776 0 8 $i Printed edition: $z 9789811660481
830 0 $a Mathematics in Industry, $x 2198-3283 ; $v 34 $3 1357435
856 4 0 $u https://doi.org/10.1007/978-981-16-6046-7
912 $a ZDB-2-SMA
912 $a ZDB-2-SXMS
950 $a Mathematics and Statistics (SpringerNature-11649)
950 $a Mathematics and Statistics (R0) (SpringerNature-43713)