unfold-methods {tensorregress} | R Documentation |
Tensor Unfolding
Description
Unfolds the tensor into a matrix, with the modes in rs
onto the rows and modes in cs
onto the columns. Note that c(rs,cs)
must have the same elements (order doesn't matter) as x@modes
. Within the rows and columns, the order of the unfolding is determined by the order of the modes. This convention is consistent with Kolda and Bader (2009).
Usage
unfold(tnsr, row_idx, col_idx)
Arguments
tnsr |
the Tensor instance |
row_idx |
the indices of the modes to map onto the row space |
col_idx |
the indices of the modes to map onto the column space |
Details
unfold(tnsr,row_idx=NULL,col_idx=NULL)
Value
matrix with prod(row_idx)
rows and prod(col_idx)
columns
References
T. Kolda, B. Bader, "Tensor decomposition and applications". SIAM Applied Mathematics and Applications 2009, Vol. 51, No. 3 (September 2009), pp. 455-500. URL: https://www.jstor.org/stable/25662308.
Examples
tnsr <- rand_tensor()
matT3<-unfold(tnsr,row_idx=2,col_idx=c(3,1))