MDS_CS MDS_CS Trainable mapping for classical scaling
W = MDS_CS(D,N)
DescriptionA linear mapping of objects given by a symmetric distance matrix D with a zero diagonal onto an Ndimensional Euclidean space such that the square distances are preserved as much as possible. D is assumed to approximate the Euclidean distances, i.e. D_{ij} = sqrt(sum_k (x_ix_j)^2). Reference(s)1. I. Borg and P. Groenen, Modern Multidimensional Scaling, Springer Verlag, Berlin, 1997. See also
