Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift.
Inigo V. SlijepcevicAnna M. M. ScaifeMike WalmsleyMicah BowlesIvy WongStanislav S. ShabalaHongming TangPublished in: CoRR (2022)
Keyphrases
- semi supervised learning
- data sets
- supervised learning
- training data
- improve the classification accuracy
- semi supervised classification
- semi supervised
- unlabeled data
- labeled data
- co training
- unsupervised learning
- semi supervised learning algorithms
- training set
- machine learning
- uci datasets
- transductive support vector machine
- benchmark data sets
- supervised classifiers
- labeled and unlabeled data
- class labels
- supervised learning algorithms
- classification accuracy
- text classification
- unlabeled samples
- active learning
- pattern recognition
- decision trees
- learning models
- label propagation
- graph based semi supervised learning
- high dimensional data
- manifold regularization
- domain adaptation
- supervised learning tasks
- transfer learning
- machine learning algorithms
- training examples
- text categorization
- training samples
- classification models
- labeled instances
- support vector
- support vector machine
- real world
- prior knowledge
- multi view
- label information
- test data
- supervised classification
- feature extraction
- learning algorithm
- data mining
- dimension reduction