clamp cross-entropy loss
8 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Matt Fetterman
le 3 Sep 2020
Commenté : Matt Fetterman
le 6 Sep 2020
the Matlab cross-entropy loss has this form:
loss = -sum(W*(T.*log(Y)))/N;
I would like to "clamp" it so that the log function output is bounded, for example it cannot be less than 100.
Can we do it?
0 commentaires
Réponse acceptée
David Goodmanson
le 3 Sep 2020
Modifié(e) : David Goodmanson
le 6 Sep 2020
Hi Matt,
z = log(Y);
z(z<100) = 100;
loss = -sum(W*(T.*z))/N;
In the link you provided, they talk about a limit of -100 rather than +100. The former appears to make more sense. Lots of possibilities for a smooth differentiable cutoff, here is one, assuming Y>=0
Ylimit = -100;
loss = -sum(W*(T.*log(Y+exp(Ylimit)))/N;
3 commentaires
Plus de réponses (0)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!