Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies.
Alena KopanicákováHardik KothariGeorge Em KarniadakisRolf KrausePublished in: CoRR (2023)
Keyphrases
- neural network
- training process
- training algorithm
- domain specific
- feedforward neural networks
- pattern recognition
- feed forward neural networks
- domain independent
- back propagation
- neural network training
- artificial intelligence
- backpropagation algorithm
- artificial neural networks
- training examples
- error back propagation
- recurrent networks
- supervised learning
- online learning
- fuzzy logic
- multi layer perceptron
- training set
- computer science
- genetic algorithm
- training samples
- test set
- edge preserving
- expert systems
- conjugate gradient
- e learning
- learning algorithm