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
- A labelled example is one thing plus its right name on a card
- The example set teaches by holding the clue that separates the two named piles
- A two-way job needs both names in its set, and more than one kind on each side
An analogy your child will recognise
Two piles on one table
Put every wet thing on one side with WET cards and every dry thing on the other with DRY cards. Anyone walking past can see what separates the two sides. That is all a set does for a smart helper.
A name card on each thing
At a class display every object carries a small card with its right name. Take the cards away and the display still shows things, but it teaches nobody. That card is the label.
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
- A labelled example is one thing plus its right name, written on its card
- The example set is all those labelled examples together, laid out by hand
- A set teaches by letting the smart helper hunt what is the same inside each named pile, then keep the clue that separates the piles
- So a wrong name hands the smart helper a wrong clue — the naming has to be right
- A two-way job needs both names in the set, and more than one kind on each side; one perfect example is not a set
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
Your neighbour wants a robot that says FRUIT or VEGETABLE for a basket. What goes into its example set, and what must each thing carry?
Rote answer
"Says you show it fruits and vegetables. Cannot say that each one needs its right name on a card, or that both names must be there."
Understood
"Says real fruits and real vegetables go on the table, each with its right name on a card, and that both names have to be in the set."
Stage 2 — Reasoning
A buddy says one perfect peel card is enough for the WET side. Why is that wrong?
Follow-up Dhee may use: Your robot sorts the bins right. What did it actually learn about peels?
Stage 3 — Application
A cousin wants a robot that says SHARP or BLUNT for pencils. What is the smallest set that could teach it?
Misconception Dhee watches for: Child offers one perfect pencil, or all pencils from one side — redirect: 'Your robot keeps the clue that separates two piles. Show me the second pile.'
Related concepts
Want your child to actually understand this?
Dhee turns this concept into a short spoken lesson — teaching, 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: "Your neighbour wants a robot that says FRUIT or VEGETABLE for a basket. What goes into its example set, and what must each thing carry?" — 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.