Deep-Bayesian-Active-Learning
Deep-Bayesian-Active-Learning copied to clipboard
Riashat
Deterministic Var Ratios and deterministic BALD
I am having problems to understand deterministic Var Ratios and deterministic BALD acquisition functions... For example, in deterministic BALD, since the neural network is deterministic, is not the mutual information equals to 0 for all points? Would this acquisition function be equivalent to random? Thanks in advance!
Yes, it is equivalent to random
On Thu, Sep 13, 2018 at 11:12 AM Raúl Soutelo Quintela < [email protected]> wrote:
I am having problems to understand deterministic Var Ratios and deterministic BALD acquisition functions... For example, in deterministic BALD, since the neural network is deterministic, is not the mutual information equals to 0 for all points? Would this acquisition function be equivalent to random? Thanks in advance!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/Riashat/Deep-Bayesian-Active-Learning/issues/4, or mute the thread https://github.com/notifications/unsubscribe-auth/AHJNe1CHPiC9dni4W82OKgy0bI66GcRZks5uanW_gaJpZM4WndTW .
