Adaptive activation functions accelerate convergence in deep and physics-informed neural networks

•We employed adaptive activation functions in deep and physics-informed neural networks.•The proposed method is very simple and it is shown to accelerate convergence in neural networks.•In particular, we approximate various nonlinear functions using deep neural networks.•Physics-informed neural netw...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of computational physics Vol. 404; no. C; p. 109136
Main Authors:	Jagtap, Ameya D., Kawaguchi, Kenji, Karniadakis, George Em
Format:	Journal Article
Language:	English
Published:	Cambridge Elsevier Inc 01.03.2020 Elsevier Science Ltd Elsevier
Subjects:	Activation Algorithms Bad minima Burgers equation Computational physics Computer simulation Convergence Critical point Deep learning benchmarks Frequencies Helmholtz equations Inverse problems Klein-Gordon equation Machine learning Mathematical analysis Neural networks Nonlinear differential equations Nonlinear equations Optimization Parameter identification Partial differential equations Physics-informed neural networks Topology Deep learning benchmarks Bad minima Inverse problems Partial differential equations Physics-informed neural networks Machine learning
ISSN:	0021-9991, 1090-2716
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!