Categorical cross-entropy loss
= Categorical cross-entropy loss
For one-hot label $y$ and predicted class probabilities $p$, categorical cross-entropy is $-\sum_ky_k\log p_k$, the negative categorical log-likelihood.
= Categorical cross-entropy loss
For one-hot label $y$ and predicted class probabilities $p$, categorical cross-entropy is $-\sum_ky_k\log p_k$, the negative categorical log-likelihood.