Self-training Converts Weak Learners to Strong Learners in Mixture Models.
Spencer FreiDifan ZouZixiang ChenQuanquan GuPublished in: CoRR (2021)
Keyphrases
- mixture model
- weak learners
- ensemble learning
- em algorithm
- gaussian mixture model
- generative model
- multi class classification
- probabilistic model
- boosting algorithms
- model selection
- learning environment
- unsupervised learning
- expectation maximization
- language model
- learning process
- cost sensitive
- linear classifiers
- multi class
- semi supervised learning
- maximum likelihood
- training set
- prediction accuracy
- computer vision
- machine learning
- weak classifiers
- binary classifiers
- semi supervised
- learning algorithm