`Frobenius()` computes the Frobenius kernel between numeric matrices.
Arguments
- DATA
A list of M matrices or data.frames containing only real numbers (class "integer", "float" or "double"). All matrices or data.frames should have the same number of rows and columns.
- cos.norm
Should the resulting kernel matrix be cosine normalized? (Defaults: FALSE).
- feat_space
If FALSE, only the kernel matrix is returned. Otherwise, the feature space is also returned. (Defaults: FALSE).
Examples
data1 <- matrix(rnorm(250000),ncol=500,nrow=500)
data2 <- matrix(rnorm(250000),ncol=500,nrow=500)
data3 <- matrix(rnorm(250000),ncol=500,nrow=500)
Frobenius(list(data1,data2,data3))
#> [,1] [,2] [,3]
#> [1,] 2.501567e+05 -198.3221 3.938937e-01
#> [2,] -1.983221e+02 249704.5579 -1.019380e+03
#> [3,] 3.938937e-01 -1019.3805 2.497023e+05