Neural Networks and Numerical Analysis / / Bruno Després.
This book uses numerical analysis as the main tool to investigate methods in machine learning and neural networks. The efficiency of neural network representations for general functions and for polynomial functions is studied in detail, together with an original description of the Latin hypercube me...
Saved in:
Superior document: | Title is part of eBook package: De Gruyter DG Plus DeG Package 2022 Part 1 |
---|---|
VerfasserIn: | |
Place / Publishing House: | Berlin ;, Boston : : De Gruyter, , [2022] ©2022 |
Year of Publication: | 2022 |
Language: | English |
Series: | De Gruyter Series in Applied and Numerical Mathematics ,
6 |
Online Access: | |
Physical Description: | 1 online resource (XVI, 158 p.) |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Other title: | Frontmatter -- Introduction -- Acknowledgement -- Contents -- 1 Objective functions, neural networks, and linear algebra -- 2 Approximation properties -- 3 A functional equation -- 4 Datasets -- 5 Stochastic gradient methods -- 6 Examples and research in the field -- Bibliography -- Index |
---|---|
Summary: | This book uses numerical analysis as the main tool to investigate methods in machine learning and neural networks. The efficiency of neural network representations for general functions and for polynomial functions is studied in detail, together with an original description of the Latin hypercube method and of the ADAM algorithm for training. Furthermore, unique features include the use of Tensorflow for implementation session, and the description of on going research about the construction of new optimized numerical schemes. |
Format: | Mode of access: Internet via World Wide Web. |
ISBN: | 9783110783186 9783110766820 9783110993899 9783110994810 9783110993868 9783110770445 |
ISSN: | 2512-1820 ; |
DOI: | 10.1515/9783110783186 |
Access: | restricted access |
Hierarchical level: | Monograph |
Statement of Responsibility: | Bruno Després. |