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.

Exposure Bias

RNNs · Level 3 of 5

Exposure Bias

A mismatch caused by training on reference histories but generating from model-produced histories.

Earlier prediction errors can lead to unfamiliar later inputs.

Example

A decoder makes one error and then conditions subsequent words on that error.

Listen to the definition and example

Audio transcript

Exposure Bias. A mismatch caused by training on reference histories but generating from model-produced histories. Earlier prediction errors can lead to unfamiliar later inputs. For example: A decoder makes one error and then conditions subsequent words on that error.

Explore this concept

Why it matters

This helps you trace information and gradient flow through sequence models.

Start with

Teacher Forcing

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.