A Randomized Framework for Discovery of Heterogeneous Mixtures

Abstract

Mixture models are the term given to models that consist of a combination of independent functions creating the distribution of points within a set. We present a framework for automatically discovering and evaluating candidate models within unstructured data. Our abstraction of models enables us to seamlessly consider different types of functions as equally possible candidates. Our framework does not require an estimate of the number of underlying models, allows points to be probabilistically classified into multiple models or identified as outliers and includes a few parameters that an analyst (not typically an expert in statistical methods) may use to adjust the output of the algorithm. We give results from our framework with synthetic data and classic data.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 04, 2011
Accession Number
ADA638064

Entities

People

  • Aditya M. Palepu
  • Jonathan Decker
  • Mark A. Livingston
  • Mikel Dermer

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Engineered Resilient Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Computations
  • Computer Science
  • Data Analysis
  • Data Sets
  • Hypotheses
  • Information Science
  • Learning
  • Machine Learning
  • Network Science
  • Supervised Machine Learning
  • Theoretical Computer Science
  • Unsupervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Artificial Intelligence
  • Computational Fluid Dynamics (CFD)