RBoost: Label Noise-Robust Boosting Algorithm Based on a Nonconvex Loss Function and the Numerically Stable Base Learners.
Qiguang MiaoYing CaoGe XiaMaoguo GongJiachen LiuJianfeng SongPublished in: IEEE Trans. Neural Networks Learn. Syst. (2016)
Keyphrases
- loss function
- gradient boosting
- boosting algorithms
- numerically stable
- label noise
- classification algorithm
- learning algorithm
- pairwise
- multi class
- expectation maximization
- training set
- objective function
- simulated annealing
- cross validation
- ensemble methods
- weak classifiers
- base learners
- similarity measure
- image processing