mwTensor (version 1.1.0)

myNMF: Independent Component Analysis (ICA) as an example of user-defined matrix decomposition.

Description

The input data is assumed to be a matrix. When algorithms of MWCAParams and CoupledMWCAParams are specified as "myNMF", This function is called in MWCA and CoupledMWCA.

Usage

myNMF(Xn, k, L1=1e-10, L2=1e-10)

Value

The output matrix which has N-rows and k-columns.

Arguments

Xn

The input matrix which has N-rows and M-columns.

k

The rank parameter (k <= min(N,M))

L1

The regularization parameter to control the sparseness (Default: 1e-10)

L2

The regularization parameter to control the overfit (Default: 1e-10)

Author

Koki Tsuyuzaki

References

Andrzej CICHOCK, et. al., (2009). Nonnegative Matrix and Tensor Factorizations.

Examples

  if(interactive()){
    # Test data
    matdata <- matrix(runif(10*20), nrow=10, ncol=20)
    # Perform NMF
    myNMF(matdata, k=3, L1=1e-1, L2=1e-2)
  }