Skip to content

Stage 1 · Beginner · F2

The slope of everything

Every AI model is a machine for taking one derivative.

12 lessons · 101 minEasy

About this chapter

Learning is one question asked over and over: if I nudge this number, does the error go up or down? This chapter builds that question from a picture rather than a definition. You will zoom in on a curve until it turns into a straight road, meet the chain rule as a row of gears, and read a gradient as an arrow that points uphill. By the end you can say what a model is doing when it trains, check a gradient by hand, and tell a real bottom from a saddle.

What you will be able to do

  1. 1

    The question every model asks

    State learning as a search for the direction that lowers the error.

    7 min
  2. 2

    How fast, not how much

    Turn two readings into a rate, and read that rate off a curve.

    7 min
  3. 3

    Zoom in until it is straight

    Say why a smooth curve looks like a line up close, and read the tilt there.

    8 min
  4. 4

    The derivative is a slope at a point

    Read the tangent anywhere on a curve and say what the sign of the derivative means there.

    9 min
  5. 5

    The rules you will actually use

    Differentiate powers and sums without looking anything up.

    8 min
  6. 6

    The chain rule is the whole game

    Send a rate through a chain of boxes by multiplying one link at a time.

    10 min
  7. 7

    One knob at a time

    Take a partial derivative and name the numbers you froze to get it.

    8 min
  8. 8

    The gradient points uphill

    Read a gradient as an arrow: a direction to climb and a steepness.

    9 min
  9. 9

    Bottoms, tops and saddles

    Tell a bottom, a top and a saddle apart when the ground is flat.

    9 min
  10. 10

    Every model is a derivative machine

    Explain why one derivative of one number is all a model ever needs.

    9 min
  11. 11

    Measure it both ways

    Measure a derivative by nudging, pick a sensible step, and use it to check the rules.

    9 min
  12. 12

    A taste of area

    Add up thin slices to get the area under a curve, and say why probability needs it.

    8 min

Before you start

Keep going

All chapters