Machine Learning Prerequisites Map

178 concepts organized by true dependency order - the mental map I use to discretize problems across CS, mathematics, and machine learning.

Why This Exists

This is how I think about technical problems - as a dependency graph. Every concept connects to prerequisites below it and unlocks capabilities above it. When I need to learn something new or explain something to a collaborator, I map the dependencies first, then optimize the path.

I built this as a mental map of how I discretize problems across CS, mathematics, and machine learning. It started as a reference guide for communicating with collaborators - when you're working across AI, infrastructure, and applied math, having a shared map of what depends on what prevents a lot of miscommunication.

Now I'm giving it away - 178 concepts organized by true dependency order, not by academic tradition. Use it however it helps you.

What Makes This Different

Learning Cost Metrics

Each concept includes quantified metrics: how many atomic elements you need to learn, the total prerequisite depth, and how many downstream concepts it unlocks. High fan-out concepts give better ROI than dead ends.

True Prerequisites, Not Course Structure

Traditional curricula group by department: "Calculus I" then "Calculus II" then "Linear Algebra." But gradient descent doesn't care about course catalogs - it needs partial derivatives, matrix multiplication, and the chain rule simultaneously. This map shows what actually depends on what.

Interactive Visualizations

34 concepts include animated visualizations built on HTML5 canvas. These are a work in progress - I'm actively improving the aesthetics and adding more. If something looks rough or you have feedback, I'd love to hear about it.

Where to Start

If you're new to the math behind ML, start with these high-ROI entry points - concepts with low prerequisite cost but high downstream unlock count:

Coordinate Systems

Cartesian coordinates, plotting points, distance formula.

Limits

Value a function approaches as input approaches a point. Foundation of calculus.

Vectors Introduction

Directed quantities with magnitude and direction. Addition and scalar multiplication.

Feedback Welcome

This is an active project. I'm refining the dependency graph, improving visualizations, and adding lessons. If you find something wrong, have a suggestion, or just want to say what's useful - reach out at admin@templeton.host or connect on LinkedIn.