Towards Computationally Feasible Deep Active Learning.
Akim TsvigunArtem ShelmanovGleb KuzminLeonid SanochkinDaniil LarionovGleb GusevManvel AvetisianLeonid ZhukovPublished in: CoRR (2022)
Keyphrases
- computationally feasible
- active learning
- bayesian analysis
- exhaustive search
- random sampling
- pool based active learning
- selective sampling
- supervised learning
- semi supervised
- machine learning
- class imbalance
- training set
- learning algorithm
- linear programming
- labeled data
- unlabeled data
- learning strategies
- transfer learning
- cost sensitive
- batch mode active learning
- learning process
- deep learning
- sample selection
- experimental design
- active learning strategies
- information systems
- batch mode
- decision trees
- rare class
- training data
- search space
- database