Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations.
Ben MoseleyAndrew MarkhamTarje Nissen-MeyerPublished in: Adv. Comput. Math. (2023)
Keyphrases
- differential equations
- neural network
- dynamical systems
- feed forward artificial neural networks
- pattern recognition
- runge kutta
- continuous functions
- numerical solution
- ordinary differential equations
- boundary value problem
- artificial neural networks
- brownian motion
- learning algorithm
- computer science
- computer vision
- nonlinear differential equations
- partial differential equations
- back propagation
- numerical methods
- fuzzy logic
- genetic algorithm