Class 3 · CBSE AI · Strand D — AI Senses
How does AI learn from examples? Supervised learning for kids
AI learns to recognise things by seeing many labelled examples. The idea behind supervised learning. For Class 3.
What this concept actually says
- AI learns to recognise things by seeing many labelled examples
- A label tells the AI what an example is called
- More varied examples help the AI learn more reliably
An analogy your child will recognise
Learning to recognise sabzi (vegetables) at a market
The first time you went to a sabzi mandi, you didn't know the vegetables. But your parent pointed to each one and said its name — 'this is brinjal, this is ladyfinger.' They showed you many different ones. That's exactly how you teach an AI: show it examples and tell it the name. Each name tag is called a label.
Flashcards for learning the alphabet
When young children learn letters, they see the letter 'A' written in many different ways — big, small, printed, handwritten, red, blue. All those different versions help the child recognise 'A' anywhere. Training an AI with examples works the same way.
Common misconceptions to watch for
- One perfect example is enough to teach an AI a category
- AI understands categories the way humans do — from a single explanation or definition
Key facts in one breath
- AI learns to recognise things through a process called supervised learning — showing it labelled examples
- A label is the correct answer attached to a training example (e.g., a photo of a cat labelled 'cat')
- The more varied and numerous the examples, the better the AI learns
- This type of learning mirrors how children learn to categorise objects
How Dhee Learning teaches this — the 3-stage question loop
Every Dhee Learning session for this concept follows three stages. We share the questions Dhee actually asks, so you can hear what a session sounds like.
Stage 1 — Surface
How did you learn what a 'mango' is? Did someone give you a definition — or did you learn some other way?
Rote answer
"Someone told me it was a mango"
Understood
"I saw mangoes many times, in different shapes and colours, and slowly I figured out what makes something a mango — not just one example"
Stage 2 — Reasoning
You want to teach an AI to recognise a 'cat.' You show it exactly one photo of one cat — a small orange cat. Later, a big fluffy white cat walks by. Do you think the AI will recognise it? Why or why not?
Follow-up Dhee may use: What kinds of different cat photos would you want to include to make sure the AI learns well? Let's make a list.
Stage 3 — Application
You want to teach an AI to tell ripe mangoes from unripe ones. What examples would you collect, and what label would you give each one?
Misconception Dhee watches for: Child thinks one perfect example per category is enough — not grasping that AI needs variety to generalise
Related concepts
Want your child to actually understand this?
Dhee turns this concept into a 15-minute spoken session — asking, listening, and probing — so your child builds the idea themselves.
Frequently asked questions
What is teaching a machine with examples (guided) — explained for kids? +
AI learns to recognise things by seeing many labelled examples. The idea behind supervised learning. For Class 3.
What's the most common mistake children make about this concept? +
One perfect example is enough to teach an AI a category
How does Dhee Learning teach this in a Class 3 session? +
Dhee opens with a question — for example: "How did you learn what a 'mango' is? Did someone give you a definition — or did you learn some other way?" — listens to your child's answer, then probes the reasoning behind it. The session ends when the child can apply the idea to a brand-new situation, not just recall it.