Cross-Entropy Loss: How Wrong Is Your Model's Guess?
Cross-entropy loss measures the penalty when a model's predicted probabilities diverge from the true labels. It's the standard loss for classification tasks, like telling a cat from a dog.
Cross-entropy loss measures the penalty for a model's predicted probabilities being different from the true labels. Think of it as the "surprise" your model feels when its guess is wrong. It's the default loss function for multi-class classification in neural networks, from image recognition to NLP. The common footgun is confusing it with accuracy: a model can be correct but unconfident (e.g., 51% sure it's a cat), leading to high loss despite high accuracy.
Read the original → Wikipedia: Cross-entropy
- #machine learning
- #loss functions
- #classification
- #neural networks
Get five bites like this every day.
Tezvyn delivers a daily feed of 60-second tech bites with quizzes to lock in what you learn.