Relief (feature selection)

Relief-based algorithms
Relief is an algorithm developed by Kira and Rendell in 1992 that takes a filter-method approach to feature selection that is notably sensitive to feature interactions.wikipedia
6 Related Articles

Feature selection

variable selectionfeaturesselecting
Relief is an algorithm developed by Kira and Rendell in 1992 that takes a filter-method approach to feature selection that is notably sensitive to feature interactions.
Dr. Mark Hall's dissertation uses neither of these, but uses three different measures of relatedness, minimum description length (MDL), symmetrical uncertainty, and relief.

Nearest neighbor search

nearest neighbornearest neighbor analysisnearest neighbors
Relief feature scoring is based on the identification of feature value differences between nearest neighbor instance pairs.

Taxicab geometry

Manhattan distanceL1 normtaxicab metric
Firstly, they find the near-hit and near-miss instances using the Manhattan (L1) norm rather than the Euclidean (L2) norm, although the rationale is not specified.

Norm (mathematics)

normEuclidean normseminorm
Firstly, they find the near-hit and near-miss instances using the Manhattan (L1) norm rather than the Euclidean (L2) norm, although the rationale is not specified.

Outline of machine learning

machine learning algorithmslearning algorithmsmachine learning