Minimum Cross-Entropy Pattern Classification and Cluster Analysis.

Abstract

This paper considers the problem of classifying an input vector of measurements by a nearest-neighbor rule applied to a fixed set of vectors. The fixed vectors are sometimes called characteristic feature vectors, codewords, cluster centers, models, reproductions, etc. The nearest-neighbor rule considered uses a non-Euclidean, information-theoretic distortion measure that is not a metric, but that nevertheless leads to a classification method that is optimal in a well-defined sense and is also computationally attractive. Furthermore, the distortion measure results in a simple method of computing cluster centroids. Our approach is based on cross-entropy minimization (also called minimum discrimination information or minimum directed divergence), and can be viewed as a refinement of a general classification method due to Kullback. The refinement exploits special properties of cross-entropy that hold when the probability densities involved happen to be minimum cross-entropy densities. The approach is a generalization of a recently-developed speech coding technique.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 10, 1980
Accession Number
ADA086158

Entities

People

  • John E. Shore
  • Robert M. Gray

Organizations

  • United States Naval Research Laboratory

Tags

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Classification
  • Coding
  • Computational Science
  • Computations
  • Coordinate Systems
  • Data Science
  • Distortion
  • Electrical Engineering
  • Information Theory
  • Measurement
  • Military Research
  • Probability
  • Random Variables
  • Security
  • Speech Analysis
  • Speech Compression

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Mathematical Modeling and Probability Theory.
  • Regression Analysis.