Heuristic Classifier Performance Bounds in High Dimensional Settings

Abstract

This paper is concerned with probability density estimation in high-dimensional settings. Simplified geometric arguments and supporting examples point to a performance bound which limits algorithm performance to that of either (1) nearest-neighbor or (2) single-kernel PDF estimators. A method of monitoring PDF estimation performance as well as recommendations for neural net and classification algorithm practitioners is provided.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 12, 2002
Accession Number
ADA477084

Entities

People

  • Paul Baggenstoss

Organizations

  • Naval Undersea Warfare Center

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Algorithms
  • Classification
  • Equations
  • Errors
  • Information Operations
  • Machine Learning
  • Military Research
  • Monitoring
  • Plotting
  • Probability
  • Random Variables
  • Training
  • Undersea Warfare

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Statistical inference.