Skip to the lesson

How AI worksLesson 2 of 6

Part 1 of 3, 0 done

14 min

One neuron, one decision

Should the bakery bake extra croissants tomorrow? Build the decision the way one artificial neuron does: weigh the clues, add them up, compare with a line.

Ticket 01 · Your turn

Score one morning

The bakery's rule works like one artificial neuron. Each clue is one if it's true and zero if not. Each clue has a weight: Saturday 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.), rain forecast −2 pointsexample (example number: Simplified example: rain forecast counts against baking extra.), market in the square 2 pointsexample (example number: Simplified example: how much the market counts toward baking extra.). Multiply each clue by its weight, add them up, and if the total is above the threshold, 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.), bake extra.

Worked case: a dry Saturday, no market. Saturday adds 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.), rain adds nothing, the market adds nothing: a total of 3 pointsexample (example number: Worked out from the example: Saturday's weight alone.). That's above 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.), so bake extra.

Your turn: a rainy Saturday, no market. What's the total?

What you know

Saturday's weight
3 points
Rain's weight
−2 points
Market's weight
2 points
Threshold
1.5 points

These numbers are our example.

points
Words to know

Spot something wrong?

Tell us what looks off. No name or email needed.

What kind of problem?

0 / 1000

We'll also send this page, the lesson, ticket 1, so we can find it. Nothing else. Privacy

·
Sources and every number

Every number

  • 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.) · Simplified example: how much Saturday counts toward baking extra.
  • −2 pointsexample (example number: Simplified example: rain forecast counts against baking extra.) · Simplified example: rain forecast counts against baking extra.
  • 2 pointsexample (example number: Simplified example: how much the market counts toward baking extra.) · Simplified example: how much the market counts toward baking extra.
  • 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.) · Simplified example: the total must be above this to bake extra.
  • 3 pointsexample (example number: Worked out from the example: Saturday's weight alone.) · Worked out from the example: Saturday's weight alone.
  • 1 pointexample (example number: Worked out from the example: Saturday's weight plus rain's weight.) · Worked out from the example: Saturday's weight plus rain's weight.
  • 5 pointsexample (example number: Worked out from the example: the total if rain were wrongly added as a plus.) · Worked out from the example: the total if rain were wrongly added as a plus.
  1. Lessons›
  2. The school›
  3. How AI works
  • ·Before this: How a chatbot picks its next word
  • ·Next: Training: learning from mistakes
Skip to the lesson

How AI worksLesson 2 of 6

Part 1 of 3, 0 done

14 min

One neuron, one decision

Should the bakery bake extra croissants tomorrow? Build the decision the way one artificial neuron does: weigh the clues, add them up, compare with a line.

Ticket 01 · Your turn

Score one morning

The bakery's rule works like one artificial neuron. Each clue is one if it's true and zero if not. Each clue has a weight: Saturday 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.), rain forecast −2 pointsexample (example number: Simplified example: rain forecast counts against baking extra.), market in the square 2 pointsexample (example number: Simplified example: how much the market counts toward baking extra.). Multiply each clue by its weight, add them up, and if the total is above the threshold, 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.), bake extra.

Worked case: a dry Saturday, no market. Saturday adds 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.), rain adds nothing, the market adds nothing: a total of 3 pointsexample (example number: Worked out from the example: Saturday's weight alone.). That's above 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.), so bake extra.

Your turn: a rainy Saturday, no market. What's the total?

What you know

Saturday's weight
3 points
Rain's weight
−2 points
Market's weight
2 points
Threshold
1.5 points

These numbers are our example.

points
Words to know

Spot something wrong?

Tell us what looks off. No name or email needed.

What kind of problem?

0 / 1000

We'll also send this page, the lesson, ticket 1, so we can find it. Nothing else. Privacy

·
Sources and every number

Every number

  • 3 pointsexample (example number: Simplified example: how much Saturday counts toward baking extra.) · Simplified example: how much Saturday counts toward baking extra.
  • −2 pointsexample (example number: Simplified example: rain forecast counts against baking extra.) · Simplified example: rain forecast counts against baking extra.
  • 2 pointsexample (example number: Simplified example: how much the market counts toward baking extra.) · Simplified example: how much the market counts toward baking extra.
  • 1.5 pointsexample (example number: Simplified example: the total must be above this to bake extra.) · Simplified example: the total must be above this to bake extra.
  • 3 pointsexample (example number: Worked out from the example: Saturday's weight alone.) · Worked out from the example: Saturday's weight alone.
  • 1 pointexample (example number: Worked out from the example: Saturday's weight plus rain's weight.) · Worked out from the example: Saturday's weight plus rain's weight.
  • 5 pointsexample (example number: Worked out from the example: the total if rain were wrongly added as a plus.) · Worked out from the example: the total if rain were wrongly added as a plus.
  1. Lessons›
  2. The school›
  3. How AI works
  • ·Before this: How a chatbot picks its next word
  • ·Next: Training: learning from mistakes