← K-Means All techniques Next: Decision Tree →

10 — Gradient Descent

Models learn by rolling downhill on a loss surface. Each step: compute the gradient (slope), move opposite to it. Learning rate controls step size — too small and you crawl, too big and you overshoot.

Position x
Loss f(x)
Gradient f'(x)
0.20
Try crank η up to 1.5 on the convex surface and step — it will overshoot and bounce around. That's why deep learning uses small η + many steps. On non-convex landscapes (right), the start point determines which local minimum you fall into.