Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems.
Sarah PerezSuryanarayana MadduIvo F. SbalzariniPhilippe PoncetPublished in: J. Comput. Phys. (2023)
Keyphrases
- inverse problems
- multi task
- multiscale
- neural network
- image reconstruction
- multi task learning
- convex optimization
- global optimization
- multitask learning
- gaussian processes
- partial differential equations
- optimization methods
- genetic algorithm
- learning tasks
- multi class
- bayesian networks
- wavelet transform
- similarity measure
- optimization problems
- image processing
- feature selection
- computationally expensive
- learning problems
- image classification
- support vector machine
- early vision