Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations.
Ben MoseleyAndrew MarkhamTarje Nissen-MeyerPublished in: CoRR (2021)
Keyphrases
- differential equations
- neural network
- feed forward artificial neural networks
- continuous functions
- dynamical systems
- numerical solution
- runge kutta
- ordinary differential equations
- pattern recognition
- boundary value problem
- computer science
- nonlinear differential equations
- brownian motion
- transmission line
- genetic algorithm
- numerical methods
- steady state
- partial differential equations
- fuzzy logic
- artificial neural networks
- search algorithm
- multiscale