I just read about Cross-entropy cost function for my work. and I see a notation that said "the minimization of cross entropy of some data is equal to maximization of their log likelihood." How can I achieve this result? How can I show that?
$\begingroup$
$\endgroup$
-
1$\begingroup$ It would help to edit your question to provide additional context. I suggest providing a full citation for where you read it, and summarizing the context. It's not clear what you mean by "minimizing the cross entropy of some data"; if the data is fixed, there is nothing to minimize. $\endgroup$ – D.W.♦ Nov 3 '19 at 19:50
-
$\begingroup$ I've written an article on the topic, but I've not yet shared with the public. However, meanwhile, you can find the answer to the question on Stats SE. $\endgroup$ – nbro Nov 7 '19 at 0:47
-
$\begingroup$ @nbro can you share the link? $\endgroup$ – Hossein Shahbodaghkhan Nov 8 '19 at 17:51
-
$\begingroup$ @HosseinShahbodaghkhan See https://stats.stackexchange.com/a/364237/82135. $\endgroup$ – nbro Nov 8 '19 at 17:54
