AI for EverybodyLearn the intelligence era with better judgment.

Your progress: 0 complete

Glossary My Map Account

Glossary My Map AccountQuick answers Choose my route History of AI Sources About this platform

You are here

Current learning moveOrient

Follow a question, situation, concept, person, or historical thread.

Do nowRead, decide, then check

Your guide

A model is a learned computational structure

Your learning move

OrientEnter through a question or situation.

Why this page exists

Explore is the connected atlas. It shows several ways to approach the same subject without pretending that every learner needs the same sequence.

What you will leave with

An AI model is a computational structure whose parameters encode patterns fitted during training. Given an input, it produces an estimate, classification, ranking, or generated continuation.

Before you begin

No prerequisite is required for topic and Quick Answer entrances.

Do this now

Choose the entrance that matches what you already have: a question, little time, a situation, or a term.

Do now on this pageRead, decide, then checkThe plan states the outcome, time, prerequisite, immediate action, and prepared continuation.Another valid routeGet a Quick AnswerUse a short orientation before deciding whether to go deeper.

Account

Quick answer · 3 min

A model is a learned computational structure

What is a model?

Plan for this page

Get a clear answer, then check that you can use it.

You will leave with: A model supplies a capability; the surrounding system determines access, use, and consequence.
Time: 3 min
Before you begin: No prerequisite. Start with your question.
Do this now: Read the direct answer before the example and active check.

Prepared next stepSeparate model, training, and product

An AI model is a computational structure whose parameters encode patterns fitted during training. Given an input, it produces an estimate, classification, ranking, or generated continuation.

The model is not the whole product: interfaces, instructions, data access, tools, rules, and people determine how it is used.

Example

Image classification

A trained model receives pixels and estimates whether an image contains a bicycle; the app decides how to display or act on that estimate.

Important limit

Model names do not describe the full system

The same model can behave differently with versions, settings, context, tools, and product controls.

Interactive model

Separate before deciding

Selected layerModel

Transforms inputs into outputs using learned parameters.

Read the complete text alternative

ModelTransforms inputs into outputs using learned parameters.
ProductWraps the model with an interface, workflow, data, and controls.

Useful distinctions

Separate the questions before judging

Model

Transforms inputs into outputs using learned parameters.

Product

Wraps the model with an interface, workflow, data, and controls.

Active check

Where should a permission to send email live?

Separate model, training, and product

Sources and scope

What supports this object

Established

Machine Learning GlossaryGoogle for Developers

Provider reference vocabulary; architecture-specific details vary.

Open source

Loading page content...

…