Constrained Fisher Scoring for a Mixture of Factor Analyzers

Abstract

This report considers the problem of learning an object appearance manifold using a spatially distributed network of sensors. Sensor nodes observe an object from different aspects and then learn a joint statistical model for the object manifold. We employ a mixture of factor analyzers model and derive a Fisher scoring method for maximum-likelihood estimation of the model parameters. We analyze convergence of the scoring method and derive stopping conditions for exiting the iterative algorithm. Simulation examples demonstrate that the proposed approach provides faster model learning over the popular expectation-maximization algorithm with similar computational requirements. Lastly, we demonstrate the efficacy of the proposed method for learning a global appearance model across the entire sensor network.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2016
Accession Number
AD1017792

Entities

People

  • Emre Ertin
  • Gene T. Whipps
  • Randolph L. Moses

Organizations

  • United States Army Research Laboratory

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Compressed Sensing
  • Computational Complexity
  • Detectors
  • Dimensionality Reduction
  • Information Science
  • Maximum Likelihood Estimation
  • Military Research
  • Networks
  • Probability
  • Sensor Networks
  • Signal Processing
  • Simulations
  • Standards
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.
  • Statistical inference.