Decoder. plain-English AI glossary

Deep learning

● Core

Machine learning with many stacked layers, so the model learns its own features instead of being handed them.

Think of it like

Teaching someone to cook by letting them ruin a thousand dishes, rather than writing out every rule for every ingredient.

Example

Image recognition jumped from hand-crafted edge detectors to deep learning around 2012, and never looked back.

How it actually works

The “deep” is literal: many layers between input and output. Each layer builds on the last, so the network discovers useful representations on its own from raw data. It’s expensive and data-hungry, but it scales in a way older methods didn’t.

For product teams

It’s the engine under nearly every modern AI product — the reason the last decade happened.

For engineers

Neural networks with many hidden layers trained by backpropagation and gradient descent.

Related

Read anything AI without the jargon

Look up any term in plain English, or save terms as you read with the free Chrome extension.

Open DecoderAdd to Chrome