Epsilon AI Learning
Ask AI
العربية
Enroll

Mathematics: descent, description, chance, and what counts as a mistake

Two ideas carry most of the mathematics you need. The first is gradient descent: step downhill on an error surface until you reach a low point. Change the learning rate and watch it crawl, converge, or bounce out entirely — that one control explains a large share of training failures. The second is describing a distribution honestly: mean, median, spread and shape, and why the mean stops being a useful summary the moment the data is skewed. Three more panels follow. A test that is 99% accurate, applied to a condition almost nobody has, and the number that matters to the person holding the positive result — which is nothing like 99%, because the healthy majority produces more false alarms than there are real cases. Then sampling: skew a population as far as you like, take averages of samples from it, and watch those averages pile into a bell anyway and tighten as the sample grows — four times the sample, half the spread, which is why a poll of a thousand can say anything about millions. And finally what counts as a mistake: two lines fitted to the same points, one charging the square of each error and one charging the error, with a single outlier you can drag. Only one line chases it, and the one that chases is the default in almost every library you will use. Two more sit underneath all of it. Correlation compresses a whole scatter into one number — and the panel shows the three ways that number lies: a perfect curve scoring zero, and pure noise with a single stray reading scoring 0.83, the same r as a genuinely strong relationship. And a matrix, which is four numbers until you apply it to every point in a grid and it becomes a movement — a stretch, a shear, a rotation. Push it until the determinant reaches zero and the whole plane collapses onto a line, which is the one thing no later matrix can undo. You do not need to derive anything here. You need to see what the numbers do when you move them, so the formulas you meet later describe something you have already watched happen.

Calculus

Gradient descent

Training is just rolling downhill. At each step the model moves against the slope of the loss. The learning rate sets the step size — too big and it overshoots, too small and it crawls.

Steps0
Current loss
0.15
-1.1
  1. Set a very small learning rate and run. It creeps downhill and never arrives. Correct direction, useless in practice — this is a model that trains for a week and learns nothing.
  2. Raise it until the steps just stop overshooting. It reaches the bottom in a handful of steps. That narrow band is what people are hunting for when they tune this.
  3. Push it higher still. The steps grow instead of shrinking and it leaves entirely. Nothing is broken — the rate is simply too large for the slope.

A moderate learning rate slides smoothly to the minimum.

Type to search across Epsilon.

navigate open esc close Open full search →

Get this download

Enter your details and we'll email you the download link right away.

We'll email the link to you — no spam.
WhatsApp Call Enroll