Mahalanobis distance metric learning algorithm for instance-based data stream classification.
Jorge Luis Rivero PérezBernardete RibeiroCarlos Morell PérezPublished in: IJCNN (2016)
Keyphrases
- mahalanobis distance
- data stream classification
- learning algorithm
- concept drift
- metric learning
- euclidean distance
- noise model
- distance metric
- data streams
- data stream mining
- covariance matrix
- data distribution
- incremental learning
- missing values
- machine learning
- learning tasks
- training data
- machine learning algorithms
- supervised learning
- knn
- classification algorithm
- active learning
- learning problems
- learning process
- multi task
- reinforcement learning
- neural network
- change detection
- semi supervised learning
- sample size
- pattern recognition
- streaming data
- distance function
- database systems