Skip to main content
HT
HerbDev Technical Consulting
← 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.

Transformer

Transformers · Level 3 of 5

Transformer

A neural architecture built around attention and feature transformations.

Transformers can be encoder-only, decoder-only, or encoder-decoder designs.

Example

A text model relates tokens through stacked attention blocks.

Listen to the definition and example

Audio transcript

Transformer. A neural architecture built around attention and feature transformations. Transformers can be encoder-only, decoder-only, or encoder-decoder designs. For example: A text model relates tokens through stacked attention blocks.

Explore this concept

A useful analogy

A group of tokens repeatedly exchanging selected information and updating their own notes.

Why it matters

This helps you trace how token representations exchange and transform information.

Technical detail

A block typically combines attention, a positionwise feedforward transformation, residual connections, and normalization. Masking determines which positions can exchange information.

Common misconception

Transformers are not limited to text or necessarily autoregressive.

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.