Skip to main content
HT
HerbDev Application Rescue
← Learning hub

Vocabulary

Understand the term. Connect the concept.

A practical dictionary of 512 AI, machine learning, mathematics, and programming terms from HerbDev’s AI Vocabulary app. Start with a definition, explore an example, then follow the concepts behind it.

Linked concepts open in a new tab. Audio reads the definition and example.

Cross-Entropy Loss

Model Training · Level 2 of 5

Cross-Entropy Loss

A loss measuring how poorly predicted probabilities match a target distribution.

For a one-hot target, it is the negative log probability of the correct class.

Example

Assigning low probability to the true class incurs a large penalty.

Listen to the definition and example

Audio transcript

Cross-Entropy Loss. A loss measuring how poorly predicted probabilities match a target distribution. For a one-hot target, it is the negative log probability of the correct class. For example: Assigning low probability to the true class incurs a large penalty.

Explore this concept

A useful analogy

Charging more when the model assigns little probability to what actually happened.

Why it matters

This helps you read a training loop and diagnose what is changing during learning.

Technical detail

H(p,q) = −Σ p_i log q_i. For a one-hot label y the loss is −log q_y.

Common misconception

Lower training cross-entropy does not ensure better deployment accuracy.

Start with

Related concepts

Quick recall question

Try answering before looking back at the definition.

Put the terminology into context: How AI works · Machine-native representations · All learning paths

Manage browser learning data

“Remove my test data” clears all AI 101 and ML 101 scores, reviews, project checklists and rating selections, plus saved vocabulary and recent history in this browser. Test entries cannot be separated from other learning progress. Cookie preferences, security protections, submitted feedback, contact emails and past analytics are kept.