How to solve the loss function of logic function and code implementation?

The loss function used in this paper is the loss function constructed by KL discretization, without formula derivation; The code part is a user-defined function, not sklearn. The loss function constructed by discrete logistic regression KL is:     Where m is the number of samples; p_1 indicates the probability that the label is 1; y^{ ...

Posted by Quest on Tue, 09 Nov 2021 19:55:55 +0100