Neural Networks and Numerical Analysis
1st Edition
Published on 22. August 2022
XVI, 158 pages
978-3-11-078318-6 (ISBN)
Description
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.
More details
Other editions
Additional editions
Bruno Després
Neural Networks and Numerical Analysis
E-Book
08/2022
1st Edition
De Gruyter
€179.95
Available for download
Bruno Després
Neural Networks and Numerical Analysis
Book
08/2022
1st Edition
De Gruyter
€179.95
Shipment within 5-7 days
Person
Bruno Després
, Sorbonne University, France.
Content
- Intro
- 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
