Skip to contents

`Linear()` computes the inner product between all possible pairs of rows of a matrix or data.frame with dimension NxD.

Usage

Linear(X, cos.norm = FALSE, coeff = NULL)

Arguments

X

Matrix or data.frame that contains real numbers ("integer", "float" or "double").

cos.norm

Should the resulting kernel matrix be cosine normalized? (Defaults: FALSE).

coeff

(optional) A vector of length D that weights each one of the features (columns). When cos.norm=TRUE, `Linear()` first does the weighting and then the cosine-normalization.

Value

Kernel matrix (dimension: NxN).

Examples

dat <- matrix(rnorm(250),ncol=50,nrow=5)
Linear(dat)
#>            [,1]       [,2]       [,3]        [,4]      [,5]
#> [1,]  59.511095 -1.2741200 -10.900658 -12.2677519  7.678785
#> [2,]  -1.274120 57.6852052  -2.967514   0.3842339  5.214374
#> [3,] -10.900658 -2.9675144  50.612273  10.4069230 -1.919365
#> [4,] -12.267752  0.3842339  10.406923  62.4838994  3.549917
#> [5,]   7.678785  5.2143740  -1.919365   3.5499166 46.013724