Stanford University Course Portal

Master Machine Learning from First Principles

Welcome to the comprehensive, interactive platform for Stanford's flagship machine learning course, CS229 (Autumn 2018) taught by Andrew Ng. Explore all 20 video lectures, official lecture notes, mathematical section reviews, problem sets with solutions, hands-on algorithm visualizers, and 120+ real student research projects.

Your Learning Progress
Autumn 2018 Master Curriculum
0%
0 / 20
Lectures Watched
0 / 5
Assignments Solved
121
Student Projects

Course Lectures

20 in-depth lectures covering Supervised Learning, Learning Theory, Deep Learning, Unsupervised Learning, and Reinforcement Learning.

Algorithm Playgrounds

Experience the mathematics in motion. Experiment with real-time gradient descent, decision boundaries, and clustering convergence.

💡 Click anywhere on the canvas to add custom data points. Red dotted lines show residual error (h_θ(x) - y).

Linear Regression Controls

Model: h_θ(x) = θ₀ + θ₁x
Cost: J(θ) = (1/2m) Σ (h_θ(x⁽ⁱ⁾) - y⁽ⁱ⁾)²
Update: θⱼ := θⱼ - α ∂J/∂θⱼ
Learning Rate (α) 0.05
Intercept (θ₀):
0.500
Slope (θ₁):
0.100
Cost J(θ):
--

Problem Sets & Solutions

Complete problem sets PS0 through PS4 with handouts, starter code, interactive Jupyter notebooks, and Stanford's official solution manuals.

Discussion Sections & Notes

Rigorous notes prepared by CS229 TAs covering linear algebra, convex optimization, hidden Markov models, Gaussian processes, and practical machine learning engineering.

Fall 2018 Student Projects

121 real student final projects with posters and research reports.

Self-Assessment Quizzes

Test your understanding of core concepts from linear models to reinforcement learning with immediate explanations.