Let us say that we have given two random variables with different prob. distributions: A = [0.1, 0, 0.5, ...] B = [0.3, 0.1, 0.03, ...]

What should I do when I want to compute the reformulated cross-entropy between those two? (log base here is 2)

This is the main equation:


The problem here is when I want to calculate 0.1 * log2(0)....

Should I skip the 0 value and its equivalent prob. from the other set? Or rather change the zero to another scalar?


Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.