Track 14 of 14 · How models read text

AI & Language Models

See how language models turn text into numbers and numbers back into text. Each lesson pairs a precise mental model with a picture you can poke at: points that move closer when meanings match, and rankings that change when you change how closeness is measured.

Builds on:Programming & Data RepresentationData Structures & Complexity

One concept, with more on the way

This track is growing deliberately. Each new lesson will earn its place and build on the ideas above it.

  1. 01EmbeddingsAn embedding is a list of numbers (a vector) that a model assigns to a piece of text so that texts with similar meaning get vectors that lie close together. The model learns the numbers from data; no single number has a meaning on its own, only the position relative to other vectors does.

Growing track

More graphics concepts will follow.

This first lesson stands on its own. Future additions will extend the same path without adding placeholder pages.

Browse all concepts