Google's practical, interactive introduction to machine learning fundamentals, linear and logistic regression, gradient descent, generalization, regularization, and neural networks.
Google's updated Machine Learning Crash Course features interactive playgrounds, visual loss surface explorers, real-world datasets, and concise engineering explanations. It walks through linear regression, logistic regression, classification thresholds, ROC-AUC, overfitting, L1/L2 regularization, and an introduction to neural networks and embeddings.
Course status is tracked independently from roadmap topic checkboxes so you can mark external courses without altering your topic mastery percentage.
Phase 2 Primary Starting Course (Modules 2.1, 2.2 & 2.4)
100% free interactive lessons, visualizations, and Colab coding exercises on Google Developers.
Status: Verified (2026-11-09)
Review these foundations before starting so you get the most out of this material:
In Phase 2: Machine Learning From Scratch
Start Phase 2 here. Complete the modules on Linear Regression, Logistic Regression, Classification Metrics, Overfitting, and Regularization alongside Modules 2.1, 2.2, and 2.4.
Learning paradigms, train/validation/test splits, parameters vs. hyperparameters, overfitting, the bias-variance tradeoff, regularization, and data leakage prevention.
Mathematical formulation and NumPy implementation of linear regression, logistic regression, MSE, binary cross-entropy, and decision boundaries.
Classification and regression metrics, confusion matrices, precision-recall tradeoffs, ROC-AUC, baseline comparisons, and leakage detection.
University course exploring the foundational concepts and algorithms of modern artificial intelligence, including search, optimization, machine learning, neural networks, and natural language processing.
Hands-on interactive micro-course covering decision trees, model validation, underfitting vs. overfitting, and random forests.
Official scikit-learn getting started tutorials and user guide for classical supervised/unsupervised learning, preprocessing, cross-validation, and evaluation metrics.