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.
Author: Bruno Després
Publisher: de Gruyter
Published: 08/08/2022
Pages: 174
Binding Type: Hardcover
Weight: 1.06lbs
Size: 9.61h x 6.69w x 0.44d
ISBN13: 9783110783124
ISBN10: 3110783126
BISAC Categories:
- Mathematics | Numerical Analysis
- Computers | Artificial Intelligence | General
- Mathematics | Applied
About the Author
Bruno Després, Sorbonne University, France.