Asymptotic improvement of supervised learning by utilizing additional unlabeled samples: normal mixture density case
Explore this paper's citation graph
Summary
It is shown that under a normal mixture density assumption for the probability density function of the feature space, the combined supervised-unsupervised learning is always superior to the supervised learning in achieving better estimates.
- Type
- article
- Published
- 1992-12-16
- Cited by
- 8
- References
- 2
- OpenAlex
- https://openalex.org/W2062926306
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:121122974
Keywords
Unsupervised learning, Semi-supervised learning, Supervised learning, Artificial intelligence, Probability density function
References
Cited by
- Enhancing Text Classification to Improve Information Filtering
- Using Unlabelled Data to Train a Multilayer Perceptron
- On the exponential value of labeled samples
- The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter
- Using Partially Labeled Data For Normal Mixture Identification With Application To Class Definition
- Enhancing Text Classification to Improve Information Filtering
- Using unlabeled data for learning classification problems
- Adaptive and Interactive Approaches to Document Analysis
Related papers
- Semi-supervised learning: a brief review
- Combined unsupervised and semi-supervised learning for data classification
- Semi-Supervised and Unsupervised Extreme Learning Machines
- A State of Art Techniques on Machine Learning Algorithms: A Perspective of Supervised Learning Approaches in Data Classification
- A Supervised Machine Learning Algorithms: Applications, Challenges, and Recommendations