Adding Domain Knowledge to SBL Through Feature Construction

  title={Adding Domain Knowledge to SBL Through Feature Construction},
  author={Christopher J. Matheus},
This paper presents two methods for adding domain knowledge to similarity-based learning through feature construction, a form of representation change in which new features are constructed from relationships detected among existing features. In the first method, domain-knowledge constraints are used to eliminate less desirable new features before they are constructed. In the second method, domain-dependent transformations generalize new features in ways meaningful to the current problem. These… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 10 references

Feature Construction: An Analytic Framework and An Application to Decision Trees

  • Matheus, J. Christopher
  • Ph.D. Dissertation, University of Illinois at…
  • 1989

Learning in an abstract space

  • Drastal, George, Raatz, Stan
  • Technical Report DCS-TR-248, Department of…
  • 1989

Shift of bias

  • Segre, Alberto
  • Sixth International Workshop on Machine Learning
  • 1989

Incremental adjustment of representations in learning

  • Schlimmer, C. Jeffrey
  • Proceedings of the Fourth International Workshop…
  • 1987

L earning efficient classification procedures and their application to chess end games

  • Quinlan, J. Ross
  • Machine Learning: An Artificial Intelligence…
  • 1983

Learning e  cient classi cationprocedures and their application to chess end games

  • J. Ross Quinlan
  • 1983
1 Excerpt

Similar Papers

Loading similar papers…