AI / ML

Switch track

AI / ML Foundations

Python and core machine-learning foundations: from programming basics to building and evaluating your first ML model.

Finish line: First ML Project

How to use your map

  • • Work top to bottom — each stage builds on the one before it.
  • • Complete a topic to unlock what it leads to.
  • • When unsure, start at your highlighted next best step.
✓ done▢ next best step (ringed) locked — finish its prerequisites first
Your progress0 / 18 done · 0%

~36 hr left · about 72 days at 30 min/day

1Start here

Python Basics

concept

The language everything else is written in — start here.

~120 min·difficulty 1/5
2Stage 2

Python Data Structures

concept

Data structures are how you hold and shape data before modelling it.

~120 min·difficulty 2/5
3Stage 3

Functions & Modules

skill

Reusable code keeps projects manageable as they grow.

~90 min·difficulty 2/5
4Stage 4

NumPy

skill

The numeric backbone of the Python data stack.

~120 min·difficulty 2/5
5Stage 5

Pandas

skill

How you actually work with real datasets.

~150 min·difficulty 3/5

Linear Algebra Basics

concept

The math that powers models under the hood.

~120 min·difficulty 3/5
6Stage 6

Data Visualization

skill

Seeing data is the first step to understanding it.

~90 min·difficulty 2/5

Descriptive Statistics

concept

The vocabulary for describing what data looks like.

~90 min·difficulty 2/5

ML Concepts

concept

What machine learning is, and when to use it.

~90 min·difficulty 2/5
7Stage 7

Probability Basics

concept

ML models reason under uncertainty — this is that language.

~120 min·difficulty 3/5

Data Preparation

skill

Most real ML work is cleaning data before modelling.

~120 min·difficulty 3/5
8Stage 8

Train/Test Split & Validation

concept

How you honestly measure whether a model works.

~90 min·difficulty 3/5

Feature Engineering

skill

Often the highest-leverage skill in practical ML.

~120 min·difficulty 4/5
9Stage 9

Linear Regression

capability

Your first predictive model — simple and foundational.

~120 min·difficulty 3/5

Classification

capability

Predicting categories — the most common ML task.

~150 min·difficulty 3/5
10Stage 10

Model Evaluation Metrics

concept

A model is only as good as how you measure it.

~90 min·difficulty 3/5
11Stage 11

Overfitting & Regularization

concept

Why models that ace training data can fail in the real world.

~120 min·difficulty 4/5
12Stage 12

First ML Project

project

Integrate everything: prepare data, model it, evaluate, and explain.

~240 min·difficulty 4/5