ON THE APPLICATION OF THE POTENTIAL FUNCTION METHOD TO PATTERN RECOGNITION AND SYSTEM IDENTIFICATION,

Abstract

The theoretical foundations of the potential function method are presented quite thoroughly in the pattern recognition literature. However, many problems are encountered when applying the potential function method to practical problems. Some of these problems are: (1) How are the potential functions formed; (2) What are the computational restrictions; (3) What a priori information is necessary or desirable. The potential function method is discussed in considerable detail to show how the two types of potential functions differ. The memory requirements of two forms (types) of the potential functions are discussed when applied to pattern classification. Application of the potential function method to system identification is accomplished by converting the system identification problem to a pattern recognition problem. (Author)

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1968
Accession Number
AD0671991

Entities

People

  • R. R. Lemke

Organizations

  • Purdue University

Tags

DTIC Thesaurus Topics

  • Classification
  • Identification
  • Pattern Recognition
  • Recognition

Readers

  • Computer Vision.
  • Statistical inference.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms