Square Pseudo-Euclidean (PE) Distance Between Two Datasets
D = PE_DISTM(A,B)
Computation of the square pseudo-Euclidean distance matrix D between two sets of vectors, A and B. The pseudo-Euclidean distance with the signature SIG (e.g. SIG = [10 5]) between vectors X and Y is computed as an indefinite 'Euclidean' distance
In a PE dataset the signature is stored in the user field, see SETSIG. This signature is derived from A. It is not stored in D as D does not contain vectors in a PE space.
D is a dataset with the labels defined by the labels of A and feature labels defined by the labels of B.
REMARKS Note that square pseudo-Euclidean distances can be negative. Zero distances can be negative due to small computational inaccuracies. The call D = PE_DISTM(A)