Towards a machine learning pipeline in reduced order modelling for inverse problems: neural networks for boundary parametrization, dimensionality reduction and solution manifold approximation.
Anna IvagnesNicola DemoGianluigi RozzaPublished in: CoRR (2022)
Keyphrases
- inverse problems
- machine learning
- dimensionality reduction
- neural network
- reduced order
- pattern recognition
- low dimensional
- closed form
- convex optimization
- image reconstruction
- global optimization
- high dimensional
- computer vision
- optimization problems
- kalman filtering
- feature selection
- feature space
- optimization method
- partial differential equations
- particle swarm optimization
- optimization methods
- principal component analysis
- evolutionary algorithm
- genetic algorithm