Maths & machine learning
The rooms that go with the maths labs, from arrows on a grid to how a language model picks its next word. Play a warm-up before its lab, and the rest alongside it.
- 1
Before you work with matrices - Linear Algebra 1
Starts from nothing: directions on a map, arrows you can add and stretch, and rules that move every point at once — which is all a matrix is. About ten minutes.
10 blocks · by Froga
- 2
Before the dot product - Linear Algebra 2
The handful of ideas Linear algebra 2 builds on: multiplying matching parts, what a right angle means for two arrows, Pythagoras, and why "similar" can mean "pointing the same way". About ten minutes.
8 blocks · by Froga
- 3
Before the machine learns
What Machine learning 1 builds on: what a labelled example is, how a score decides spam or not, what "training" actually changes, and why you keep some examples back. About ten minutes.
7 blocks · by Froga
- 4
Before the network
What Machine learning 2 builds on: the logic gates again, what makes a neuron fire, what a feature is, and why a perfect score on practice questions can mislead. About ten minutes.
7 blocks · by Froga
- 5
Conditional Probability and Bayes' Theorem
An introduction to conditional probability and Bayes' theorem, showing how to update a belief when new evidence arrives. Written for anyone comfortable with basic percentages who wants to see why intuition about tests and probabilities is so often wrong.
6 blocks · by Froga
- 6
Before the chance machine
What Chance machines builds on: a chance worked out by counting, why all the chances add up to 100%, and when to multiply chances and when to add them. About ten minutes.
7 blocks · by Froga
- 7
Before words become arrows
What Words as arrows builds on: why a computer needs words as numbers, when two arrows point the same way, subtracting one arrow from another, and analogies in plain words. About ten minutes.
7 blocks · by Froga
- 8
AI Fundamentals: How Large Language Models Actually Work
Tokens, parameters, attention, hallucination — the mechanics behind ChatGPT and every model like it, explained once so the vocabulary stops being intimidating.
10 blocks · by Froga