Identification of New Clusters from Labeled Data Using Mixture Models.
Yujung KimJaejik KimPublished in: J. Comput. Biol. (2022)
Keyphrases
- mixture model
- labeled data
- data points
- unlabeled data
- semi supervised
- semi supervised learning
- model based clustering
- generative model
- unsupervised learning
- supervised learning
- em algorithm
- training data
- gaussian mixture model
- probabilistic model
- text classification
- active learning
- clustering algorithm
- learning algorithm
- transfer learning
- class labels
- model selection
- maximum likelihood
- labeled training data
- labeled and unlabeled data
- expectation maximization
- unlabeled samples
- hierarchical clustering
- data distribution
- prior knowledge
- training examples
- cluster analysis
- co training
- language model
- pattern recognition
- text categorization
- high dimensional data
- data sets
- target domain
- neural network
- feature selection
- decision trees
- pairwise
- high dimensional
- dimensionality reduction
- test data
- data mining
- learning tasks
- document clustering
- feature space
- training set