Learning in the presence of concept drift and hidden contexts

@article{Widmer2004LearningIT,
  title={Learning in the presence of concept drift and hidden contexts},
  author={G. Widmer and M. Kubat},
  journal={Machine Learning},
  year={2004},
  volume={23},
  pages={69-101}
}
  • G. Widmer, M. Kubat
  • Published 2004
  • Computer Science
  • Machine Learning
  • On-line learning in domains where the target concept depends on some hidden context poses serious problems. A changing context can induce changes in the target concepts, producing what is known as concept drift. We describe a family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear. The general approach underlying all these algorithms consists of (1) keeping only a window of currently trusted examples and hypotheses; (2… CONTINUE READING

    Topics from this paper.

    The problem of concept drift: definitions and related work
    • 803
    • Highly Influenced
    • PDF
    Learning in Environments with Unknown Dynamics: Towards more Robust Concept Learners
    • 40
    • Highly Influenced
    • PDF
    1 A Survey on Concept Drift Adaptation
    • 25
    • Highly Influenced
    • PDF
    Using additive expert ensembles to cope with concept drift
    • 235
    • PDF
    Detecting and adapting to drifting concepts
    • 8
    Just-In-Time Classifiers for Recurrent Concepts
    • 112
    • PDF
    Boosting classifiers for drifting concepts
    • 138
    • PDF
    Learning with Drift Detection
    • 906
    • Highly Influenced
    • PDF
    Learning from streaming data with concept drift and imbalance: an overview
    • 166
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES
    Effective Learning in Dynamic Environments by Explicit Context Tracking
    • 174
    • PDF
    Incremental Learning from Noisy Data
    • 387
    • Highly Influential
    • PDF
    COBBIT - A Control Procedure for COBWEB in the Presence of Concept Drift
    • 30
    • PDF
    Instance-Based Learning Algorithms
    • 3,346
    • Highly Influential
    • PDF
    A theory of the learnable
    • 1,952
    • PDF
    Learning Time-Varying Concepts
    • 85
    • Highly Influential
    • PDF
    Experiments with incremental concept formation: UNIMEM
    • 89
    • PDF
    Robust Classification with Context-Sensitive Features
    • 50
    • PDF
    The Role of Forgetting in Learning
    • 159
    • PDF