UID:
almafu_9961059965002883
Format:
1 online resource (VI, 126 p.)
ISBN:
9783111025551
Series Statement:
De Gruyter Textbook
Content:
The goal of this book is to provide a mathematical perspective on some key elements of the so-called deep neural networks (DNNs). Much of the interest in deep learning has focused on the implementation of DNN-based algorithms. Our hope is that this compact textbook will offer a complementary point of view that emphasizes the underlying mathematical ideas. We believe that a more foundational perspective will help to answer important questions that have only received empirical answers so far. The material is based on a one-semester course Introduction to Mathematics of Deep Learning" for senior undergraduate mathematics majors and first year graduate students in mathematics. Our goal is to introduce basic concepts from deep learning in a rigorous mathematical fashion, e.g introduce mathematical definitions of deep neural networks (DNNs), loss functions, the backpropagation algorithm, etc. We attempt to identify for each concept the simplest setting that minimizes technicalities but still contains the key mathematics.
Note:
Frontmatter --
,
Contents --
,
1 About this book --
,
2 Introduction to machine learning: what and why? --
,
3 Classification problem --
,
4 The fundamentals of artificial neural networks --
,
5 Supervised, unsupervised, and semisupervised learning --
,
6 The regression problem --
,
7 Support vector machine --
,
8 Gradient descent method in the training of DNNs --
,
9 Backpropagation --
,
10 Convolutional neural networks --
,
A Review of the chain rule --
,
Bibliography --
,
Index
,
Issued also in print.
,
In English.
Additional Edition:
ISBN 9783111025803
Additional Edition:
ISBN 9783111024318
Language:
English
Subjects:
Computer Science
DOI:
10.1515/9783111025551
URL:
https://doi.org/10.1515/9783111025551
URL:
https://www.degruyter.com/isbn/9783111025551
URL:
Volltext
(URL des Erstveröffentlichers)
URL:
https://doi.org/10.1515/9783111025551
URL:
https://www.degruyter.com/isbn/9783111025551
