A discrete-time neurodynamic approach to sparsity-constrained nonnegative matrix factorization

Xinqi Li, Jun Wang, Sam Kwong

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Sparsity is a desirable property in many nonnegative matrix factorization (NMF) applications.Although some level of sparseness ofNMFsolutions can be achieved by using regularization, the resulting sparsity depends highly on the regularization parameter to be valued in an ad hoc way. In this letter we formulate sparse NMF as a mixed-integer optimization problem with sparsity as binary constraints. A discrete-time projection neural network is developed for solving the formulated problem. Sufficient conditions for its stability and convergence are analytically characterized by using Lyapunov’s method. Experimental results on sparse feature extraction are discussed to substantiate the superiority of this approach to extracting highly sparse features.

Original languageEnglish
Pages (from-to)1531-1562
Number of pages32
JournalNeural computation
Volume32
Issue number8
DOIs
Publication statusPublished - 1 Aug 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'A discrete-time neurodynamic approach to sparsity-constrained nonnegative matrix factorization'. Together they form a unique fingerprint.

Cite this