Dimensionality Reduction in Big Data with Nonnegative Matrix Factorization

Abstract

The grantee shall investigate new methods of dimensionality reduction based on Non-negative Matrix Factorization. This project has two goals: 1) extend simplicial NMF and newly formulate Generative NMF, both with concise interpretability and high quality, 2) design fast and fully parallel distributed algorithms for these two rich NMF models.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 23, 2016
Source ID
FA23861514006

Entities

People

  • Tu-bao Ho

Organizations

  • Air Force Office of Scientific Research
  • Japan Advanced Institute of Science and Technology
  • United States Air Force

Tags

Readers

  • Linear Algebra
  • Neural Network Machine Learning.