An Improved Kernel Minimum Square Error Classification Algorithm Based on $L_{2, 1}$ -Norm Regularization.
Zhonghua LiuShan XueLin ZhangJiexin PuHaijun WangPublished in: IEEE Access (2017)
Keyphrases
- square error
- classification algorithm
- norm regularization
- multiple kernel learning
- convex optimization
- kernel learning
- canonical correlation analysis
- support vector machine
- k nearest neighbor
- noise sensitivity
- document classification
- kernel methods
- kernel function
- total variation
- objective function
- sparse representation
- class labels
- knn
- training set
- naive bayes
- support vector
- learning algorithm
- loss function
- learning problems
- machine learning
- clustering algorithm
- multi class
- learning process
- feature space
- positive definite
- semi supervised
- multi task
- kernel matrix