Machine Learning Crash Course

Google's fast-pacedpractical introduction to machine learningfeaturing a series of animated videosinteractive visualizationsand hands-on practice exercises.
Start Crash Course Browse course modules View prerequisites Help Center
Since 2018millions of people worldwide have relied on Machine Learning Crash Course to learn how machine learning worksand how machine learning can work for them. We're delighted to announce the launch of a refreshed version of MLCC that covers recent advances in AIwith an increased focus on interactive learning. Watch this video to learn more about the new-and-improved MLCC.

Course Modules

Each Machine Learning Crash Course module is self-containedso if you have prior experience in machine learningyou can skip directly to the topics you want to learn. If you're new to machine learningwe recommend completing modules in the order below.

ML Models

These modules cover the fundamentals of building regression and classification models.

An introduction to linear regressioncovering linear modelslossgradient descentand hyperparameter tuning.
An introduction to logistic regressionwhere ML models are designed to predict the probability of a given outcome.
An introduction to binary classification modelscovering thresholdingconfusion matricesand metrics like accuracyprecisionrecalland AUC.

Data

These modules cover fundamental techniques and best practices for working with machine learning data.

Learn how to analyze and transform numerical data to help train ML models more effectively.
Learn the fundamentals of working with categorical data: how to distinguish categorical data from numerical data; how to represent categorical data numerically using one-hot encodingfeature hashingand mean encoding; and how to perform feature crosses.
An introduction to the characteristics of machine learning datasetsand how to prepare your data to ensure high-quality results when training and evaluating your model.

Advanced ML models

These modules cover advanced ML model architectures.

An introduction to the fundamental principles of neural network architecturesincluding perceptronshidden layersand activation functions.
Learn how embeddings allow you to do machine learning on large feature vectors.
New
An introduction to large language modelsfrom tokens to Transformers. Learn the basics of how LLMs learn to predict text outputas well as how they're architected and trained.

Real-world ML

These modules cover critical considerations when building and deploying ML models in the real worldincluding productionization best practicesautomationand responsible engineering.

Learn how a machine learning production system works across a breadth of components.
New
Learn principles and best practices for using automated machine learning.
Learn principles and best practices for auditing ML models for fairnessincluding strategies for identifying and mitigating biases in data.