Translations:Cross-Entropy Loss/22/en

    From Marovi AI

    For multi-class classification with $ K $ classes, the true label is typically a one-hot vector $ \mathbf{y} $ with $ y_c = 1 $ for the correct class $ c $. The predicted probabilities $ \hat{\mathbf{y}} $ are obtained via the Softmax Function:

    Retrieved from "https://marovi.ai/index.php?title=Translations:Cross-Entropy_Loss/22/en&oldid=17553"