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.

Epoch

Model Training · Level 2 of 5

Epoch

One pass through a defined training dataset.

Sampling, streaming, and distributed setups may define passes differently.

Example

A trainer has processed every example once.

Listen to the definition and example

Audio transcript

Epoch. One pass through a defined training dataset. Sampling, streaming, and distributed setups may define passes differently. For example: A trainer has processed every example once.

Explore this concept

A useful analogy

One circuit around a finite collection of training examples.

Why it matters

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

Technical detail

If N examples are visited once in batches of size B, an epoch has approximately ceil(N/B) steps when the last partial batch is kept.

Common misconception

An epoch is not one optimizer step unless the entire dataset fits into that step.

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.