Technical note: Bias and the quantification of stability

@article{Turney1995TechnicalNB,
  title={Technical note: Bias and the quantification of stability},
  author={Peter D. Turney},
  journal={Machine Learning},
  year={1995},
  volume={20},
  pages={23-33}
}
Research on bias in machine learning algorithms has generally been concerned with the impact of bias on predictive accuracy. We believe that there are other factors that should also play a role in the evaluation of bias. One such factor is the stability of the algorithm; in other words, the repeatability of the results. If we obtain two sets of data from the same phenomenon, with the same underlying probability distribution, then we would like our learning algorithm to induce approximately the… CONTINUE READING
BETA

Similar Papers

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 65 CITATIONS, ESTIMATED 97% COVERAGE

Improving Stability of Decision Trees

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Knowledge Acquisition from Examples Via Multiple Models

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A framework to induce more stable decision trees for pattern classification

  • Pattern Analysis and Applications
  • 2016
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Characterizing Model Errors and Di erencesStephen

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Types of Cost in Inductive Concept Learning

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

1997
2018

CITATION STATISTICS

  • 7 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

An empirical technique for quantifying preferential bias in inductive concept learners

C. Schaffer
  • Unpublished manuscript. Department of Computer
  • 1992
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

p.gp.cs.cmu.edu, cd /usr/jair/pub

J. R. Quinlan
  • 1992
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Overfitting avoidance as bias

  • Machine Learning
  • 1993
VIEW 3 EXCERPTS

Inductive learning using generalized distance measures

  • Defense, Security, and Sensing
  • 1992
VIEW 1 EXCERPT

Quantifying inductive bias: AI learning systems and Valiant’s learning framework.Artificial

  • 1988
VIEW 2 EXCERPTS