Artificial Intelligence / Unit 8 AI 0433 short lesson, about 20 seconds
The Nudging Rule
Captions available
The idea
The perceptron learns by nudging: a correct verdict changes nothing, and every error shifts each weight a step toward what would have made the right answer.
In practice
Called ripe when truly unripe: the score ran high, so subtract each feature's value from its weight, and one from the balance.
Where people slip
Successes teach nothing — the rule is error-driven, local, and cheap by design.
Your place on the trail
Every lesson rests on earlier ones and opens later ones. Tap any to jump.
Something wrong in this lesson? Flag it · Sources for Artificial Intelligence