1
$\begingroup$

I need to reproduce the result of Xu, Xiaocong, et al, 2016 paper . Mutual information code already was done and work fine. Can anyone help me to write Jeffrey’s divergence code? Because the I use Jeffrey’s divergence function in file exchange code, but I think it has an issue.

In the aforementioned paper the j-div is better because it has wider distance between correct result and wrong one, but in my case, the opposite happens, MI is better (see the image below).

Paper result:

enter image description here

My result:

enter image description here

$\endgroup$

1 Answer 1

1
$\begingroup$

According to the paper the definition is given by:

enter image description here

All you need is to find a function which implements the Kullback Leibler Divergence and apply it twice (Will be inefficient).

In MATLAB you may use relativeEntropy() or use getKullbackLeibler() which seems a decent implementation.

In the latter you may just replace KLD = nansum( P .* log2( P./Q ) ); with JLD = nansum( (P - Q) .* log2( P./Q ) ); for Jeffrey’s Divergence.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.