On the approximation of the solution of partial differential equations by artificial neural networks trained by a multilevel Levenberg-Marquardt method.
Henri CalandraSerge GrattonElisa RicciettiXavier VasseurPublished in: CoRR (2019)
Keyphrases
- artificial neural networks
- levenberg marquardt
- closed form
- numerical methods
- partial differential equations
- energy functional
- neural network
- anisotropic diffusion
- bp neural network
- numerical scheme
- numerical solution
- training algorithm
- bundle adjustment
- high order
- back propagation
- least squares
- pairwise
- image processing