Google Machine Learning Crash Course
A structured free introduction to machine learning fundamentals with interactive exercises, covering the vocabulary and the core techniques properly. Good if you want the traditional foundations rather than a fast track to shipping.
Course
AI & Machine Learning
About 20 hours
Beginner
Free
What it is
Google's own introductory course, built from the internal training they give engineers, with interactive visualisations and coding exercises throughout.
What it covers
Linear and logistic regression, loss functions and gradient descent, overfitting and regularisation, feature engineering, neural network basics, classification metrics, and the parts people skip such as data quality, fairness and evaluation.
Where it fits against the alternatives
It is more conventional than fast.ai and less deep than a university course. Its particular strength is the sections on evaluation and data problems, which are where real machine learning projects usually fail and which practical courses tend to rush.
Best for: engineers who want the standard vocabulary and the theory in a structured order, at no cost.
Ready to start?
Opens on Google in a new tab.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.