Train Once and Use Forever: Solving Boundary Value Problems in Unseen Domains with Pre-trained Deep Learning Models.
Hengjie WangRobert PlanasAparna ChandramowlishwaranRamin BostanabadPublished in: CoRR (2021)
Keyphrases
- learning models
- pre trained
- training examples
- boundary value problem
- learning algorithm
- learning tasks
- loss function
- machine learning
- training data
- boundary conditions
- semi supervised learning
- conditional random fields
- machine learning algorithms
- classification models
- transfer learning
- differential equations
- control signals
- learning problems
- small number
- variational inequalities
- training set
- labeled data
- active learning
- supervised learning
- partial differential equations
- light source
- data sets
- learning environment
- maximum likelihood
- hidden markov models