One equation, published in 1805, still runs inside every neural network.
M1 · The Best Straight Line
Fit a line by eye, then let algebra find a better one, then let a walk downhill find the same one again. Those three routes to one answer are machine learning in miniature. Along the way the loss becomes a bowl you can see, extra features become extra columns, and a curve turns out to be a straight line in disguise. The chapter ends on the two things that go wrong: a model that memorizes its data, and a score of 0.98 that means nothing at all.
- Fit It by Eye First
- Why We Square the Error
- The Loss Surface Is a Bowl
- The Exact Answer
- The Same Answer, Step by Step
- More Than One Input
- Put the Features on One Scale
- Curves From a Linear Model
- Trying Too Hard
- Ridge and Lasso as a Budget
- R Squared and Its Traps
- Where This Lives Inside Every Network