annotate toolboxes/FullBNT-1.0.7/KPMstats/KLgauss.m @ 0:cc4b1211e677
tip
initial commit to HG from
Changeset:
646 (e263d8a21543) added further path and more save "camirversion.m"
| author |
Daniel Wolff |
| date |
Fri, 19 Aug 2016 13:07:06 +0200 |
| parents |
|
| children |
|
| rev |
line source |
|
Daniel@0
|
1 function kl = KLgauss(P, Q)
|
|
Daniel@0
|
2 %The following computes D(P||Q), the KL divergence between two zero-mean
|
|
Daniel@0
|
3 %Gaussians with covariance P and Q:
|
|
Daniel@0
|
4 % klDiv = -0.5*(log(det(P*inv(Q))) + trace(eye(N)-P*inv(Q)));
|
|
Daniel@0
|
5
|
|
Daniel@0
|
6 R = P*inv(Q);
|
|
Daniel@0
|
7 kl = -0.5*(log(det(R))) + trace(eye(length(P))-R);
|
|
Daniel@0
|
8
|
|
Daniel@0
|
9 %To get MI, just set P=cov(X,Y) and Q=blockdiag(cov(X),cov(Y)).
|
