Skip to content
InfratoApp

Google · Course

Machine Learning Crash Course

Machine Learning Crash Course is Google’s own introduction to how machine learning works, taught in short modules with interactive and programming exercises. Google says it has been used by millions of people since 2018 and that the refreshed version covers recent advances in AI.

Open at Google ↗Common questions

Who it suits

  • People with little or no machine learning background: Google recommends going through all the material in order.
  • People with some background who want a more current and complete understanding: take the modules that interest you.
  • Not the right place to learn ML libraries in depth: Google says it teaches concepts and does not cover APIs such as Keras in depth.

What it covers

  • Linear regression, logistic regression and classification, including loss, gradient descent and metrics such as precision, recall and AUC.
  • Working with numerical and categorical data, and how datasets, generalization and overfitting affect results.
  • Neural networks and embeddings.
  • An introduction to large language models, from tokens to Transformers.
  • Production ML systems, AutoML and ML fairness.

Before you start

  • Prework: familiarity with Python, NumPy and pandas.
  • Prerequisites in algebra, linear algebra and statistics, and optionally calculus.

Common questions about Machine Learning Crash Course

What is Machine Learning Crash Course?
It is Google’s course on machine learning concepts, in modules with exercises, from linear regression through neural networks and large language models.
Do I need to know Python first?
Google lists familiarity with Python, NumPy and pandas as prework, so yes, a working knowledge helps before you start.
Do I have to install anything?
Google says the programming exercises run on Colaboratory in your browser with no setup, and work best on Chrome or Firefox on a desktop.
Will it teach me Keras?
Not in depth. Google says the course focuses on concepts and uses libraries like Keras in exercises, and points to the Keras developer guides for more.

More like this

Keep learning on Infrato

Where this comes from

Written from Google’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Google and this is not an endorsement.