CUR+NMF for learning spectral features from large data matrix

Abstract

Nonnegative matrix factorization (NMF) is a popular method for multivariate analysis of nonnegative data. It was successfully applied to learn spectral features from EEG data. However, the size of a data matrix grows, NMF suffers from dasiaout of memorypsila problem. In this paper we present a memory-reduced method where we downsize the data matrix using… (More)
DOI: 10.1109/IJCNN.2008.4634009

Topics

10 Figures and Tables

Cite this paper

@article{Lee2008CURNMFFL, title={CUR+NMF for learning spectral features from large data matrix}, author={Hyekyoung Lee and Seungjin Choi}, journal={2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)}, year={2008}, pages={1592-1597} }