How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis.
Shuai ZhangMeng WangSijia LiuPin-Yu ChenJinjun XiongPublished in: CoRR (2022)
Keyphrases
- unlabeled data
- semi supervised learning
- co training
- semi supervised
- theoretical analysis
- hidden layer
- labeled data
- semi supervised classification
- training set
- active learning
- back propagation
- supervised learning
- text classification
- artificial neural networks
- neural network
- learning algorithm
- training data
- labeled and unlabeled data
- training examples
- machine learning
- transfer learning
- feed forward
- learning rate
- unsupervised learning
- multilayer perceptron
- multi view
- data points
- recurrent neural networks
- rbf neural network
- radial basis function
- class labels
- prior knowledge
- artificial intelligence
- pairwise
- neural nets