國立高雄大學圖資館 |

登入

回首頁

Geometry of deep learninga signal processing perspective /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Geometry of deep learningby Jong Chul Ye.
其他題名:	a signal processing perspective /
作者:	Ye, Jong Chul.
出版者:	Singapore :Springer Singapore :2022.
面頁冊數:	xvi, 330 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Deep learning (Machine learning)Mathematics.
電子資源:	https://doi.org/10.1007/978-981-16-6046-7
ISBN:	9789811660467$q(electronic bk.)

Geometry of deep learninga signal processing perspective /
Ye, Jong Chul.

Geometry of deep learninga signal processing perspective /[electronic resource] :by Jong Chul Ye. - Singapore :Springer Singapore :2022. - xvi, 330 p. :ill., digital ;24 cm. - Mathematics in industry,v. 372198-3283 ;. - Mathematics in industry ;16..

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$q(electronic bk.)

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

919976
Deep learning (Machine learning)
--Mathematics.

LC Class. No.: Q325.73 / .Y4 2022

Dewey Class. No.: 006.310151

Geometry of deep learninga signal processing perspective /
LDR:03599nmm a2200337 a 4500 001 619605
003 DE-He213
005 20220112011318.0
006 m d
007 cr nn 008maaau
008 221103s2022 si s 0 eng d
020 $a 9789811660467$q(electronic bk.)
020 $a 9789811660450$q(paper)
024 7 $a 10.1007/978-981-16-6046-7 $2 doi
035 $a 978-981-16-6046-7
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.73 $b .Y4 2022
072 7 $a PBKF $2 bicssc
072 7 $a MAT037000 $2 bisacsh
072 7 $a PBKF $2 thema
082 0 4 $a 006.310151 $2 23
090 $a Q325.73 $b .Y37 2022
100 1 $a Ye, Jong Chul. $3 919975
245 1 0 $a Geometry of deep learning $h [electronic resource] : $b a signal processing perspective / $c by Jong Chul Ye.
260 $a Singapore : $b Springer Singapore : $b Imprint: Springer, $c 2022.
300 $a xvi, 330 p. : $b ill., digital ; $c 24 cm.
490 1 $a Mathematics in industry, $x 2198-3283 ; $v 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 0 $a Deep learning (Machine learning) $x Mathematics. $3 919976
650 0 $a Geometry. $3 183883
650 1 4 $a Functional Analysis. $3 274845
650 2 4 $a Differential Geometry. $3 273785
650 2 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Mathematical Models of Cognitive Processes and Neural Networks. $3 567118
650 2 4 $a Mathematical and Computational Biology. $3 514442
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Mathematics in industry ; $v 16. $3 560066
856 4 0 $u https://doi.org/10.1007/978-981-16-6046-7
950 $a Mathematics and Statistics (SpringerNature-11649)