Physics-informed Karhunen-Loéve and neural network approximations for solving inverse differential equation problems.
Jing LiAlexandre M. TartakovskyPublished in: J. Comput. Phys. (2022)
Keyphrases
- differential equations
- neural network
- numerical methods
- dynamical systems
- boundary value problem
- back propagation
- difference equations
- continuous functions
- initial conditions
- numerical solution
- neural nets
- multilayer perceptron
- markov random field
- higher order
- multiresolution
- image analysis
- artificial neural networks
- pairwise
- feature extraction
- machine learning