Active training of physics-informed neural networks to aggregate and interpolate parametric solutions to the Navier-Stokes equations.
Christopher J. ArthursAndrew P. KingPublished in: J. Comput. Phys. (2021)
Keyphrases
- neural network
- training process
- training algorithm
- navier stokes equations
- feedforward neural networks
- computer science
- multi layer perceptron
- back propagation
- pattern recognition
- feed forward neural networks
- neural network structure
- neural network training
- test set
- optimal solution
- genetic algorithm
- training phase
- backpropagation algorithm
- fuzzy systems
- recurrent neural networks
- feed forward
- radial basis function
- online learning
- fuzzy logic
- artificial neural networks
- training set
- solution space
- recurrent networks
- training patterns
- parametric models
- training samples
- machine learning