Dissemin is shutting down on January 1st, 2025

Published in

Massachusetts Institute of Technology Press, Neural Computation, 6(26), p. 1128-1168, 2014

DOI: 10.1162/neco_a_00576

Links

Tools

Export citation

Search in Google Scholar

On Nonnegative Matrix Factorization Algorithms for Signal-Dependent Noise with Application to Electromyography Data

Journal article published in 2014 by Karthik Devarajan, Vincent C. K. Cheung ORCID
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Green circle
Preprint: archiving allowed
Green circle
Postprint: archiving allowed
Orange circle
Published version: archiving restricted
Data provided by SHERPA/RoMEO

Abstract

Nonnegative matrix factorization (NMF) by the multiplicative updates algorithm is a powerful machine learning method for decomposing a high-dimensional nonnegative matrix V into two nonnegative matrices, W and H, where [Formula: see text]. It has been successfully applied in the analysis and interpretation of large-scale data arising in neuroscience, computational biology, and natural language processing, among other areas. A distinctive feature of NMF is its nonnegativity constraints that allow only additive linear combinations of the data, thus enabling it to learn parts that have distinct physical representations in reality. In this letter, we describe an information-theoretic approach to NMF for signal-dependent noise based on the generalized inverse gaussian model. Specifically, we propose three novel algorithms in this setting, each based on multiplicative updates, and prove monotonicity of updates using the EM algorithm. In addition, we develop algorithm-specific measures to evaluate their goodness of fit on data. Our methods are demonstrated using experimental data from electromyography studies, as well as simulated data in the extraction of muscle synergies, and compared with existing algorithms for signal-dependent noise.