camir-aes2014: toolboxes/distance_learning/mlr/distance/setDistanceFull.m annotate

first hg version after svn

rev	line source
wolffd@0	1 function D = setDistanceFull(X, W, Ifrom, Ito)
wolffd@0	2 %
wolffd@0	3 % D = setDistanceFull(X, W, Ifrom, Ito)
wolffd@0	4 %
wolffd@0	5 % X = d-by-n data matrix
wolffd@0	6 % W = d-by-d PSD matrix
wolffd@0	7 % Ifrom = k-by-1 vector of source points
wolffd@0	8 % Ito = j-by-1 vector of destination points
wolffd@0	9 %
wolffd@0	10 % D = n-by-n matrix of squared euclidean distances from Ifrom to Ito
wolffd@0	11 % D is sparse, and only the rows corresponding to Ifrom and
wolffd@0	12 % columns corresponding to Ito are populated.
wolffd@0	13
wolffd@0	14 [d,n] = size(X);
wolffd@0	15 [vecs,vals] = eig(0.5 * (W + W'));
wolffd@0	16 L = real(abs(vals)).^0.5 * vecs';
wolffd@0	17
wolffd@0	18 Vfrom = L * X(:,Ifrom);
wolffd@0	19
wolffd@0	20 if nargin == 4
wolffd@0	21 Vto = L * X(:,Ito);
wolffd@0	22 else
wolffd@0	23 Vto = L * X;
wolffd@0	24 Ito = 1:n;
wolffd@0	25 end
wolffd@0	26
wolffd@0	27 D = distToFrom(n, Vto, Vfrom, Ito, Ifrom);
wolffd@0	28 end

Mercurial > hg > camir-aes2014