University course exploring the foundational concepts and algorithms of modern artificial intelligence, including search, optimization, machine learning, neural networks, and natural language processing.
Taught by Brian Yu and David J. Malan, CS50 AI bridges classical algorithmic AI and modern statistical machine learning. Its lectures and Python coding projects cover optimization, probability/uncertainty, supervised learning (nearest neighbors, perceptrons, SVMs, regularization), neural networks, and attention/language fundamentals.
Course status is tracked independently from roadmap topic checkboxes so you can mark external courses without altering your topic mastery percentage.
Phase 2 Comprehensive University Course (Modules 2.1–2.3)
All lecture videos, notes, slides, and hands-on Python project specifications are 100% free on cs50.harvard.edu/ai/.
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
Focus on the lectures and projects covering Optimization, Learning (Supervised ML & Regularization), and Neural Networks.
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.
K-Nearest Neighbors, Decision Trees, Random Forests, Naive Bayes, SVMs, K-Means Clustering, PCA, and Gradient Boosting.
A comprehensive introduction to Python programming, covering functions, variables, control flow, exceptions, libraries, unit testing, file I/O, and object-oriented programming.
Google's practical, interactive introduction to machine learning fundamentals, linear and logistic regression, gradient descent, generalization, regularization, and neural networks.
Free interactive textbook combining mathematical explanations, code, and practical deep-learning concepts.