Derivatives
A derivative tells you how fast something changes. It is the key idea behind how an AI model learns. You find slopes by hand and check them in Python. Then you see how a slope shows which way to turn a weight.
New words
- Slope
- How steep a line is: how much it rises for each step forward.
- Derivative
- The slope of a curve at one single point.
- Nudge
- A very small change in the input, often called h.
- Power rule
- A shortcut: the derivative of x² is 2x, of x³ is 3x².
- Error
- A number that shows how wrong the model is. Lower is better.
- Weight
- A number inside a model that it learns during training.
What you will learn
- Why does AI need derivatives?
- What is a slope?
- What is a derivative?
- Is there a shortcut?
- What do positive, negative and zero slopes mean?
- How does a slope help train a model?
- Try it: walk on a curve
- Common mistakes
- Explain it to a friend
- Key takeaways
10 quiz questions at the end.
The full lesson, with interactive demos and the quiz, opens after you sign in with Google. It is free.