The NMFTU Toolbox holds a collection of Non-negative Matrix Factorization (NMF) algorithms implemented for Matlab


Algorithms:

mm: Multiplicative updates method using euclidean distance measure.

cjlin: Projected gradient method

prob: Probabilistic non-negative matrix factorization.

als: Alternating least squares.

alsobs: Alternating least squares with optimal brain surgeon.

Usage:

[W,H] = nmf(X,K,alg,maxiter,speak)

W: output matrix

H: output matrix

X: input matrix

K: number of components

alg: algorithm to use

maxiter: maximum number of iterations

speak: print to screen

Demonstrations:

PET: NMF on a PET dataset

Text: NMF used on a three different datasets; Email, medical, and CNN.