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.

Iteration

Model Training · Level 2 of 5

Iteration

One repetition of an algorithm's update loop.

An iteration and an epoch are usually different units.

Example

A training loop completes one optimizer update.

Listen to the definition and example

Audio transcript

Iteration. One repetition of an algorithm's update loop. An iteration and an epoch are usually different units. For example: A training loop completes one optimizer update.

Explore this concept

A useful analogy

One turn of an algorithm’s repeated loop.

Why it matters

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

Technical detail

A training iteration commonly executes a forward pass, backward pass, and update, but accumulation can separate these units.

Common misconception

An iteration is not necessarily a complete pass over a dataset.

Start with

Loop

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.