<電子ブック>
Geometry of Deep Learning : A Signal Processing Perspective / by Jong Chul Ye
(Mathematics in Industry. ISSN:21983283 ; 37)
版 | 1st ed. 2022. |
---|---|
出版者 | (Singapore : Springer Nature Singapore : Imprint: Springer) |
出版年 | 2022 |
大きさ | XVI, 330 p. 1 illus : online resource |
著者標目 | *Ye, Jong Chul author SpringerLink (Online service) |
件 名 | LCSH:Functional analysis LCSH:Geometry, Differential LCSH:Artificial intelligence LCSH:Neural networks (Computer science) LCSH:Biomathematics FREE:Functional Analysis FREE:Differential Geometry FREE:Artificial Intelligence FREE:Mathematical Models of Cognitive Processes and Neural Networks FREE:Mathematical and Computational Biology |
一般注記 | 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 HTTP:URL=https://doi.org/10.1007/978-981-16-6046-7 |
目次/あらすじ
所蔵情報を非表示
電子ブック | 配架場所 | 資料種別 | 巻 次 | 請求記号 | 状 態 | 予約 | コメント | ISBN | 刷 年 | 利用注記 | 指定図書 | 登録番号 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
電子ブック | オンライン | 電子ブック |
|
Springer eBooks | 9789811660467 |
|
電子リソース |
|
EB00201145 |
書誌詳細を非表示
データ種別 | 電子ブック |
---|---|
分 類 | LCC:QA319-329.9 DC23:515.7 |
書誌ID | 4000141971 |
ISBN | 9789811660467 |
類似資料
この資料の利用統計
このページへのアクセス回数:4回
※2017年9月4日以降