000 -LEADER |
fixed length control field |
a |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
fixed length control field |
220610b xxu||||| |||| 00| 0 eng d |
020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
International Standard Book Number |
9789811660450 |
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
Classification number |
006.31 |
Item number |
YEJ |
100 ## - MAIN ENTRY--PERSONAL NAME |
Personal name |
Ye, Jong Chul |
245 ## - TITLE STATEMENT |
Title |
Geometry of deep learning : a signal processing perspective |
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) |
Name of publisher, distributor, etc |
Springer, |
Date of publication, distribution, etc |
2022 |
Place of publication, distribution, etc |
Singapore : |
300 ## - PHYSICAL DESCRIPTION |
Extent |
xvi, 330 p. ; |
Other physical details |
ill., |
Dimensions |
25 cm |
365 ## - TRADE PRICE |
Price amount |
74.99 |
Price type code |
EUR |
Unit of pricing |
86.00 |
490 ## - SERIES STATEMENT |
Series statement |
Mathematics in industry, 1612-3956 |
Volume number/sequential designation |
v.37 |
504 ## - BIBLIOGRAPHY, ETC. NOTE |
Bibliography, etc |
Includes bibliographical references and index. |
520 ## - SUMMARY, ETC. |
Summary, etc |
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 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
Topical term or geographic name as entry element |
Functional Analysis |
|
Topical term or geographic name as entry element |
Differential Geometry |
|
Topical term or geographic name as entry element |
Artificial Intelligence |
|
Topical term or geographic name as entry element |
Mathematical Models |
|
Topical term or geographic name as entry element |
Cognitive Processes |
|
Topical term or geographic name as entry element |
Neural Networks |
|
Topical term or geographic name as entry element |
Mathematical and Computational Biology |
|
Topical term or geographic name as entry element |
Activation function |
|
Topical term or geographic name as entry element |
Algorithmic robutness |
|
Topical term or geographic name as entry element |
Bias-variance trade-off |
|
Topical term or geographic name as entry element |
Convex optimization |
|
Topical term or geographic name as entry element |
Deep convolutional framelets |
|
Topical term or geographic name as entry element |
Encoder-decoder CNN |
|
Topical term or geographic name as entry element |
Feature space |
|
Topical term or geographic name as entry element |
Gradient descent method |
|
Topical term or geographic name as entry element |
Kernel SVM |
|
Topical term or geographic name as entry element |
Loss surfaces |
|
Topical term or geographic name as entry element |
Neural tangent Kernel (NTK) |
|
Topical term or geographic name as entry element |
Positive definite |
|
Topical term or geographic name as entry element |
Representer theorem |
|
Topical term or geographic name as entry element |
Sigmoid function |
|
Topical term or geographic name as entry element |
Training data |
|
Topical term or geographic name as entry element |
Universal approximation theorem |
|
Topical term or geographic name as entry element |
Vanishing gradient problem |
|
Topical term or geographic name as entry element |
Weight clipping |
942 ## - ADDED ENTRY ELEMENTS (KOHA) |
Source of classification or shelving scheme |
|
Item type |
Books |