nmf {Matrix} |
R Documentation |
NMF Model fitting function
Description
Fit a non-negative matrix factorization model to a given target matrix.
The function allows for different update rules and initialization
methods, and can fit different NMF variants.
Usage
nmf(x, rank,
max.iterations = 1000,
tolerance = 0.001,
epsilon = 1E-20);
Arguments
x
target data to fit, i.e. a matrix-like objec
rank
specification of the factorization rank. It is usually a single numeric value, but
other type Of values are possible (e.g. matrix), For which specific methods are
implemented. See for example methods nmf,matrix,matrix,ANY.
If rank Is a numeric vector With more than one element, e.g. a range Of ranks,
then nmf performs the estimation procedure described in nmfEstimateRank. [as integer]
Details
Authors
sciBASIC.NET
Value
this function returns data object of type
any kind.
clr value class
Examples
[Package
Matrix version 5.0.1.2389
Index]