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.
By:
Bruno Després Imprint: De Gruyter Country of Publication: Germany Dimensions:
Height: 240mm,
Width: 170mm,
Weight: 434g ISBN:9783110783124 ISBN 10: 3110783126 Series:De Gruyter Series in Applied and Numerical Mathematics Pages: 174 Publication Date:22 August 2022 Audience:
Professional and scholarly
,
Undergraduate
,
Undergraduate
Format:Hardback Publisher's Status: Active