Non-negative matrix factorization as a feature selection tool for maximum margin classifiers.
Mithun Das GuptaJing XiaoPublished in: CVPR (2011)
Keyphrases
- maximum margin
- negative matrix factorization
- support vector
- feature selection
- support vector machine
- multi task
- multiple kernel learning
- matrix factorization
- feature set
- hyperplane
- document clustering
- principal component analysis
- svm classifier
- sparse representation
- text categorization
- feature subset
- pattern classification
- machine learning
- learning algorithm
- feature extraction
- cross validation
- kernel function
- spectral clustering
- text classification
- training data
- bayesian networks
- markov networks
- model selection
- unsupervised learning
- data sets
- learning problems
- learning tasks
- information extraction
- data points
- feature space