ML Anthology

Adapting to Drift in Continuous Domains (Extended Abstract)

Miroslav Kubat, Gerhard Widmer
ECML-PKDD 1995 pp. 307-310
doi:10.1007/3-540-59286-5_74 /ecmlpkdd/1995/kubat1995ecml-adapting/

Abstract

The experiments demonstrate that FRANN compares favourably with FLORA4 in the presence of concept drift. Learning is possible from examples described by symbolic as well as by numeric attributes, and because of its representation formalism (RBF networks, which realize a kind of prototype weighting scheme) FRANN is particularly effective in capturing concepts with nonlinear boundaries.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Kubat and Widmer. "Adapting to Drift in Continuous Domains (Extended Abstract)." European Conference on Machine Learning, 1995. doi:10.1007/3-540-59286-5_74

Markdown

[Kubat and Widmer. "Adapting to Drift in Continuous Domains (Extended Abstract)." European Conference on Machine Learning, 1995.](https://mlanthology.org/ecmlpkdd/1995/kubat1995ecml-adapting/) doi:10.1007/3-540-59286-5_74

BibTeX

@inproceedings{kubat1995ecml-adapting,
  title     = {{Adapting to Drift in Continuous Domains (Extended Abstract)}},
  author    = {Kubat, Miroslav and Widmer, Gerhard},
  booktitle = {European Conference on Machine Learning},
  year      = {1995},
  pages     = {307-310},
  doi       = {10.1007/3-540-59286-5_74},
  url       = {https://mlanthology.org/ecmlpkdd/1995/kubat1995ecml-adapting/}
}