Cross-Entropy
Domain: Math & Logic for AI
🎯 Motivation
Measures the difference between two probability distributions. Used as a loss function in classification.
📋 Concrete Example
If the true label is cat but the model predicts only 10% cat, cross-entropy loss is high. If 90%, it is low.
🔗 Analogy
Like a penalty for being wrong and confident - you lose points for assigning low probability to the truth.