AI Glossary Term

What is Cross-Entropy Loss?

Definition

A common objective function used to train classification models by penalizing incorrect probabilities.

Related terms

Loss Function
A mathematical objective that quantifies prediction error during training.
Annotation
Human-added labels or metadata used to train or evaluate machine learning models.
Ground Truth
Trusted reference labels used to train or evaluate model outputs.
Calibration
How well a model's confidence scores match actual correctness probabilities.
Classification
A task where a model assigns an input to one or more predefined categories.
Classifier
A model designed specifically for classification tasks.

Learn more in our free guides

Entropy-Based SamplingFocal Loss for Imbalanced DetectionTriplet Loss and Metric LearningSiamese Networks and Triplet Loss
Browse the full AI GlossaryExplore all free AI guides