New to AI? You only need three labels to begin: the company makes the technology, the model is the engine, and the app is what you open. A method is a recipe developers use to build or teach AI.

Made byMicrosoft researchers
What kind of thing?Picture engine design
Can I use it directly?Usually works inside another app. You do not need to learn its design to use AI.
An illustrated dog, flower and bicycle inside a picture frame, with a camera and magnifying glass.
Look at the dog, flower and bicycle. Recognising what is there and finding where it is are two different AI jobs.

See the idea in three steps

Start withAn animal photo
AI helps withRecognise visual patterns
You getA suggested label: dog

A simple illustration of the idea. Results depend on the model, training and app.

A familiar way to picture it

An everyday analogyImagine a long learning route with helpful shortcuts that let earlier information reach later stages.

An analogy helps you understand the main idea. It is not a description of every technical detail.

A simple ResNet example

A suitably trained app looks at a photograph and labels it “dog”.

1

A developer chooses categories, such as cats and dogs.

2

A ResNet-based system learns patterns from labelled pictures.

3

It uses those patterns to suggest a category for a new photo.

How is ResNet different from YOLO?

ResNet is a network design often used for recognising and classifying images. YOLO is associated with finding objects and their locations. A picture label and a box around an object answer different questions.

Where can I try it or learn more?

Usually works inside another app. You do not need to learn its design to use AI.

Microsoft research ↗

A maker’s page or research page may explain the technology rather than provide a chat box. Available models, features and access can change.

A small activity for you

Look at a street photo. First name the main subject. Then point to every vehicle. Notice the difference between classifying a picture and locating objects.

You do not need to memorise model sizes or write a program to understand this lesson. First explain the idea in your own words. If you want to build an app later, the official resources are your next step.

Common beginner questions

How is ResNet different from YOLO?

ResNet is a network design often used for recognising and classifying images. YOLO is associated with finding objects and their locations. A picture label and a box around an object answer different questions.

Who made ResNet?

Microsoft researchers. Usually works inside another app. You do not need to learn its design to use AI.

How can I start learning this topic?

Look at a street photo. First name the main subject. Then point to every vehicle. Notice the difference between classifying a picture and locating objects.

Keep learning

These related lessons help you compare the names without getting lost in technical details.

VGG Neural Network Explained: VGG16 and VGG19 Basics →YOLO Object Detection Explained with Everyday Examples →

See all 20 AI names and the seven-day learning plan →

Sources and review date

Reviewed 3 November 2026. Examples and analogies are written for beginners. Product facts are linked to the maker, original project or research below.