Non-negative sparse coding

TL;DR

This paper introduces a non-negative sparse coding method with an efficient multiplicative algorithm for data decomposition, basis learning, and demonstrates its effectiveness through simulations.

Contribution

It presents a novel non-negative sparse coding technique with a simple multiplicative algorithm and basis learning from data, enhancing data representation methods.

Findings

Effective data decomposition demonstrated in simulations

Efficient multiplicative algorithm for sparse coding

Basis vectors can be learned from observed data

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.