Cross-entropy loss (binary)

==$L_{\mathrm{CE}}(\hat{y},y)=-(y\log (\hat{y})+(1-y)\log (1-\hat{y}))$==

• $\hat{y}$: true distribution
• $y$: estimated distribution

Why?

• calculate the distance between two probability distributions

🔗 Links

🚶 Logistic Regression