0
Your cart

Your cart is empty

Books > Science & Mathematics > Mathematics > Calculus & mathematical analysis > Functional analysis

Buy Now

Geometry of Deep Learning - A Signal Processing Perspective (Hardcover, 1st ed. 2022) Loot Price: R1,197
Discovery Miles 11 970
You Save: R609 (34%)
Geometry of Deep Learning - A Signal Processing Perspective (Hardcover, 1st ed. 2022): Jong Chul Ye

Geometry of Deep Learning - A Signal Processing Perspective (Hardcover, 1st ed. 2022)

Jong Chul Ye

Series: Mathematics in Industry, 37

 (sign in to rate)
Was R1,806 Loot Price R1,197 Discovery Miles 11 970 | Repayment Terms: R112 pm x 12* You Save R609 (34%)

Bookmark and Share

Expected to ship within 12 - 19 working days

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.

General

Imprint: Springer Verlag, Singapore
Country of origin: Singapore
Series: Mathematics in Industry, 37
Release date: 2022
First published: 2022
Authors: Jong Chul Ye
Dimensions: 235 x 155 x 29mm (L x W x T)
Format: Hardcover
Pages: 330
Edition: 1st ed. 2022
ISBN-13: 978-981-16-6045-0
Categories: Books > Computing & IT > Applications of computing > Signal processing
Books > Science & Mathematics > Mathematics > Calculus & mathematical analysis > Functional analysis
Books > Science & Mathematics > Mathematics > Geometry > Differential & Riemannian geometry
Books > Science & Mathematics > Mathematics > Applied mathematics > Mathematics for scientists & engineers
Books > Science & Mathematics > Mathematics > Applied mathematics > Mathematical modelling
Books > Computing & IT > Applications of computing > Artificial intelligence > General
Promotions
LSN: 981-16-6045-X
Barcode: 9789811660450

Is the information for this product incomplete, wrong or inappropriate? Let us know about it.

Does this product have an incorrect or missing image? Send us a new image.

Is this product missing categories? Add more categories.

Review This Product

No reviews yet - be the first to create one!

You might also like..

Fourier Acoustics - Sound Radiation and…
Earl G. Williams Hardcover R2,941 Discovery Miles 29 410
Problems And Solutions In Banach Spaces…
Willi-Hans Steeb, Wolfgang Mathis Hardcover R3,596 Discovery Miles 35 960
Extremum Seeking through Delays and PDEs
Tiago Roux Oliveira, Miroslav Krstic Hardcover R3,418 R3,083 Discovery Miles 30 830
A Mathematical Journey to Quantum…
Salvatore Capozziello, Wladimir-Georges Boskoff Hardcover R2,531 Discovery Miles 25 310
Bloch-type Periodic Functions: Theory…
Yong-kui Chang, Gaston Mandata N'G'Uerekata, … Hardcover R2,064 Discovery Miles 20 640
Operator Theory and Harmonic Analysis…
Alexey N. Karapetyants, Vladislav V. Kravchenko, … Hardcover R6,433 Discovery Miles 64 330
The Mathematics of Errors
Nicolas Bouleau Hardcover R3,918 Discovery Miles 39 180
Fractals - Form, Chance and Dimension
Benoit B. Mandelbrot Hardcover R1,059 Discovery Miles 10 590
A Birman-Schwinger Principle in Galactic…
Markus Kunze Hardcover R3,893 Discovery Miles 38 930
Theory
Steven Lord, Fedor Sukochev, … Hardcover R4,400 Discovery Miles 44 000
Operator Theory - Proceedings of the…
Aref Jeribi Hardcover R4,136 Discovery Miles 41 360
Finite-Dimensional Vector Spaces
Paul Halmos Hardcover R632 Discovery Miles 6 320

See more

Partners