Step-by-step learning path

Learn machine learning with Python.

A learning path for beginners: understand AI, set up Python and Jupyter, explore data, then build and evaluate a first model. Follow the lessons in order as you prepare to use a model in a web application.

Start with lesson 1 Explore the topics

3 published lessons · 13 planned in this part

Available lessons

Each lesson builds on the previous one. Choose your starting point or continue where you left off.

  1. Lesson 1
    Cards showing a decision tree, regression, a deep learning network and generated content on a light desk.

    AI, machine learning and deep learning: understanding the differences

    Understand AI, machine learning, deep learning and generative AI through one concrete problem, then follow the steps from training a model to using it in an application.

  2. Lesson 2
    Workspace for installing Python with uv: a laptop displaying an editor, notebook cells and a terminal, beside a notebook and a Python pin.

    Install Python with uv, VS Code and Jupyter

    Set up a Python project on Windows with uv, configure VS Code and Jupyter, then check the notebook’s kernel and library versions.

  3. Lesson 3
    Python basics: a variable, a list of scores and a function, beside a laptop and the Python emblem.

    Python basics: variables, lists, dictionaries, conditions, loops and functions

    Learn Python basics through 11 concepts: variables, strings, lists, dictionaries, conditions, loops and functions, with a notebook and a solved exercise.

Start with clear steps

The first lesson needs no code or installation. The second sets up Python, uv, VS Code and Jupyter on Windows. The third introduces your first Python instructions.

  • Start with lesson 1 if you are new to AI.
  • Keep the same project folder and environment across the lessons.
  • Run the cells and work through the exercises before continuing.

To go further with the language and its libraries, explore the category Explore Python for machine learning.

The programme for part 1

The next lessons are being prepared progressively. Each one becomes available here when it is published.

Show all planned lessons
  1. Lesson 1: AI, machine learning and deep learningWhat these concepts cover, and what a model cannot do.
    Available
  2. Lesson 2: Set up your Python environmentPython, uv, VS Code and Jupyter, ready for the learning path.
    Available
  3. Lesson 3: Python basicsVariables, lists, dictionaries, conditions, loops and functions.
    Available
  4. Lesson 4: Work with data from an Excel fileRead, check, select and export a table with Python.
    In preparation
  5. Lesson 5: Read and write a CSV fileTurn a text file into data you can work with.
    In preparation
  6. Lesson 6: Calculate with NumPyArrays of numbers, without writing a loop.
    In preparation
  7. Lesson 7: Explore with pandasRead, describe, filter and group a dataset.
    In preparation
  8. Lesson 8: Visualise dataChoose and read a chart with matplotlib and seaborn.
    In preparation
  9. Lesson 9: Supervised learningLearn from examples whose answers are known.
    In preparation
  10. Lesson 10: Statistics and probabilitySummarise data and reason about uncertainty.
    In preparation
  11. Lesson 11: Distances and gradient descentHow a model adjusts its parameters.
    In preparation
  12. Lesson 12: A first linear regressionA model written from scratch, then evaluated.
    In preparation
  13. Lesson 13: Frame a machine learning projectAvoid data leakage and read a confusion matrix.
    In preparation

Content categories

Choose a category to explore a subject. To learn step by step, follow the lessons in the learning path.

Understanding AI

Concepts, tasks, how models work and their limits. Understand what a model does and choose a useful question.

2 published articles

Python for machine learning

Language, environment, libraries and project code. Write, read and reuse Python code.

4 published articles

Data, statistics and visualisation

Data quality, exploration, preparation and charts. Explain the data and prepare it correctly.

Lessons in this category are in preparation.

Machine learning

Models, evaluation and interpretation. Compare results and justify the choice of a model.

Lessons in this category are in preparation.

Web applications with models

Streamlit, APIs, interfaces and model use. Build an application that uses a prediction.

Lessons in this category are in preparation.

Deep learning

Neural networks, training and comparison. Explore models further after learning the foundations.

Lessons in this category are in preparation.