GENERALIZED SCALE-FREE MATRIX APPROXIMATION WITH VARIABLE LOSS FUNCTION,

Abstract

A rationale is developed for least square generalized scale free matrix approximation with variable loss function. A computing algorithm is provided which appears to give results close to the theoretical least sqaure criterion. Special cases of the general case are identified as previously developed factor analytic techniques. The method is applied to seven sets of experimental data. (Author)

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1968
Accession Number
AD0664506

Entities

People

  • Paul Horst

Organizations

  • University of Washington

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Experimental Data

Readers

  • Computational Modeling and Simulation
  • Operations Research

Technology Areas

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