Non-negative sparse coding

2002/02/11 by Patrik O. Hoyer, Hoyer, Patrik O. · 2 citations
Computer Science · Engineering · #Blind Source Separation Techniques #Face and Expression Recognition #Sparse and Compressive Sensing Techniques #cs.CV #cs.NE

paper · pdf · doi:10.48550/arxiv.cs/0202009

arxiv created 2002/02/11 · arxiv updated 2009/11/30

Abstract

Non-negative sparse coding is a method for decomposing multivariate data into non-negative sparse components. In this paper we briefly describe the motivation behind this type of data representation and its relation to standard sparse coding and non-negative matrix factorization. We then give a simple yet efficient multiplicative algorithm for finding the optimal values of the hidden components. In addition, we show how the basis vectors can be learned from the observed data. Simulations demonstrate the effectiveness of the proposed method.

Cited by

• Difference-of-Convex Elastic Net for Compressed Sensing
• An Efficient ADMM Method for Ratio-Type Nonconvex and Nonsmooth Minimization in Sparse Recovery

Related

• Non-negative matrix factorization with sparseness constraints
• A Unified Framework for Sparse Non-Negative Least Squares using\n Multiplicative Updates and the Non-Negative Matrix Factorization Problem
• Learning nonnegative matrix factorizations from compressed data
• An Efficient Algorithm for Non-Negative Matrix Factorization with Random Projections
• Convex Coding