Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation

Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. GD type optimization schemes can be regarded as temporal discretization methods for the gradient fl...

Full description

Bibliographic Details
Main Authors: Simon Eberle, Arnulf Jentzen, Adrian Riekert, Georg S. Weiss
Format: Article
Language:English
Published: AIMS Press 2023-03-01
Series:Electronic Research Archive
Subjects:
deep learning
artificial intelligence
optimization
gradient flow
kurdyka-łojasiewicz inequalities
Online Access:https://www.aimspress.com/article/doi/10.3934/era.2023128?viewType=HTML

Internet

https://www.aimspress.com/article/doi/10.3934/era.2023128?viewType=HTML

Similar Items