Learn AI by listening, watching and doing

Ten connected courses take you from your first line of Python to machine learning, LLM apps, deployed models and your first research paper. Every lesson can be read aloud, animated, explored in live demos and run as real code, right in your browser.

Every lesson narrated Code that runs in the page Free, no sign-up

Ten courses, one path

Start with the foundations (skip what you already know). Machine Learning is the core; after Deep Learning, choose Computer Vision, NLP or Generative AI. Flask & Deployment puts your models online, and the research course takes you to your first paper.

Foundations

Programming, data and maths: skip any you already know.

Start here

Python

Your first programming language

Variables, loops, functions, data structures, files, classes and Pythonic code, then NumPy, pandas, plotting and the developer tools every AI engineer uses.

Before this: No prior knowledge.

22 topics73 hours11 code examples

SQL & Databases

Ask questions of your data

SELECT and filtering, grouping, joins, subqueries, CTEs and window functions, designing tables, and SQL for machine learning, with a live database in the page.

Before this: Nothing, though a little Python helps for the last topic.

15 topics34 hours2 code examples

Maths for AI

The maths behind the models

Notation, vectors and matrices, derivatives and gradients, probability and statistics, eigenvectors, optimisation, information theory and numerical stability, each with interactive pictures.

Before this: School algebra. Python helps for the code examples.

17 topics49 hours1 code examples

Core AI

The heart of the path: machine learning and deep learning, then vision and language.

Machine Learning

From zero to job-ready

Python, NumPy and pandas, the maths you need, core ML algorithms, model evaluation, deployment, LLM basics, tools and libraries, and a job-ready portfolio.

Before this: Python and Maths for AI (or equivalent). SQL helps.

47 topics259 hours11 code examples7 story missions

Deep Learning

Build and debug neural networks

Tensors, autograd and networks from scratch; optimisers, regularisation and debugging; CNNs, RNNs and transformers; transfer learning, generative models and efficient deployment.

Before this: Machine Learning (at least the core and Deep learning sections).

18 topics99 hours16 code examples4 story missions

Computer Vision

Teach computers to see

Images as data and augmentation, classification with pretrained CNNs, object detection, segmentation, Vision Transformers and CLIP, robustness and fairness.

Before this: Deep Learning.

10 topics49 hours6 code examples2 story missions

Natural Language Processing

Work with language and LLMs

Tokenisation, embeddings, text classification and NER, text generation and evaluation, fine-tuning LLMs with SFT, LoRA and preference tuning.

Before this: Deep Learning.

9 topics42 hours7 code examples2 story missions

Build and go further

Turn models into products, and learn to do research.

Generative AI & LLM Apps

Build apps with LLMs

How LLMs work, prompt engineering, calling model APIs with structured output and tools, retrieval-augmented generation, agents, evaluation, guardrails and safety, and multimodal models.

Before this: Python. Machine Learning helps; Deep Learning and NLP go deeper.

13 topics40 hours

Flask & Deployment

Put your models online

How the web works, Flask apps, templates and forms, databases, REST APIs, serving an ML model, testing, Docker and deploying to the cloud with monitoring.

Before this: Python and SQL. Machine Learning for the model-serving topics.

12 topics41 hours

Becoming an AI Researcher

From first paper to funded PhD

How research works, experiments and statistics, writing and publishing, a capstone paper of your own, and a PhD application kit with funding guidance.

Before this: Machine Learning, plus Deep Learning and one of Computer Vision or NLP.

26 topics213 hours5 code examples4 story missions

Build real projects

Ten end-to-end projects built to industry standard, from problem framing to a monitored API, with every step explained.

Project 1 is ready: Will the patient show up?Predict missed appointments, decide who gets a reminder call from real costs, and ship it as a tested API. 23 steps, full repository included.
See the projects
New: the code playgroundRun Python with pandas and scikit-learn, SQL on sample databases, R with ggplot2, and JavaScript, right in your browser. No sign-up.
Open the playground
Python reference and 60+ example programsEvery built-in function and string, list and dictionary method explained with a runnable example, plus classic beginner programs with code and output.
Browse the examples

Every topic, six ways in

Use whichever helps you understand. They are all in every course.

Gradient descent: at the current weight we measure the slope, and step the other way.
A small learning rate takes tiny, safe steps, but needs many of them.

Coming next

The site is built to grow. Your progress in the current courses stays when new ones arrive.

Reinforcement LearningAgents that learn by trial and error, from bandits and Q-learning to policy gradients.
Responsible AIFairness, privacy, explainability and the laws that govern AI systems.
Your suggestionMore courses will be added as the site grows.