Should supervised discretisation always be trusted unreservedly? On combining characteristics of supervised and unsupervised discretisation algorithms in two-step processing.
Urszula StanczykGrzegorz BaronPublished in: KES (2023)
Keyphrases
- semi supervised
- learning algorithm
- unsupervised methods
- unsupervised learning
- supervised methods
- supervised learning
- real time
- supervised classification
- significant improvement
- theoretical analysis
- word sense induction
- weakly supervised
- unsupervised feature selection
- data processing
- supervised and unsupervised learning
- discriminant projection
- worst case
- unsupervised and semi supervised
- feature selection
- supervised and semi supervised
- computationally efficient
- data clustering
- times faster
- optimization problems
- simulated annealing
- dimensionality reduction
- active learning
- genetic algorithm