K-Nearest Neighbor Rules.

Abstract

The k - Nearest Neighbor Rule is one specific example of a statistical decision rule. The report deals with a specific modification of this rule. The topics included are the distribution of risk of any sample - based decision rule in terms of the training set sample size, rule structure and underlying probability densities, evaluation of a k - nearest neighbor rule, the metric used in non parametric decision rules. (Author)

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1971
Accession Number
AD0731221

Entities

People

  • Edward A. Patrick
  • Frederic Philip Fischer Ii

Organizations

  • Purdue University

Tags

DTIC Thesaurus Topics

  • Probability
  • Test And Evaluation
  • Training

Readers

  • Neural Network Machine Learning.
  • Regression Analysis.