Weekly Materials
Work through each week at your own pace. Click any resource to open the PDF reader.
Introduction & Linear Regression
Introduction to ML, model representation, cost function, gradient descent. Lectures 1–3.
Multivariate Linear Regression
Multiple features, gradient descent in practice, normal equation. Lectures 4–5. Exercise 1.
Logistic Regression & Regularization
Classification, logistic regression, regularization. Lectures 6–7. Exercise 2.
Neural Networks: Representation
Non-linear hypotheses, neurons and the brain, neural network model. Lecture 8. Exercise 3.
Neural Networks: Learning
Cost function, backpropagation, gradient checking. Lecture 9. Exercise 4.
Advice for Applying ML
Evaluating hypotheses, bias vs variance, learning curves. Lectures 10–11. Exercise 5.
Support Vector Machines
Large margin classification, kernels, SVMs in practice. Lecture 12. Exercise 6.
Unsupervised Learning
Clustering, K-means, dimensionality reduction, PCA. Exercise 7.
Large Scale Machine Learning
Stochastic gradient descent, map-reduce. Lecture 17.
Application Example: Photo OCR
Photo OCR pipeline, sliding windows, artificial data. Lecture 18.
Interactive Simulators
Hands-on visual tools to build intuition for key ML concepts. Click, drag, and experiment.
Linear Regression
Click to add data points and watch gradient descent fit a line in real time.
🌍Gradient Descent
Visualize gradient descent on 2D contour plots with adjustable learning rate.
📉Cost Function
See how the cost function changes as you adjust the hypothesis parameters.
🔍Logistic Regression
Add two-class data points and visualize the sigmoid decision boundary.
🧠Neural Network
Interactive network diagram showing forward propagation and weight visualization.
🔄Backpropagation
Step through forward and backward passes to understand gradient computation.
⚖Regularization
Compare underfitting, good fit, and overfitting with adjustable lambda and degree.
🎯K-Means Clustering
Step through the K-means algorithm with Voronoi region visualization.
📐PCA
Visualize principal components, projection lines, and data reconstruction.
🛡SVM
Explore maximum margin classification, soft margins, and RBF kernel effects.
Extra Resources
Supplementary materials from Stanford CS229 and beyond.
Linear Algebra Review
CS229 supplemental notes covering vectors, matrices, and key linear algebra concepts.
📄CS229 Lecture Notes
Detailed lecture notes from Stanford CS229 covering supervised and unsupervised learning.
⚙Probability Review
CS229 probability and statistics primer for machine learning foundations.
📊Machine Learning & Stocks
Applied machine learning techniques for stock market prediction and analysis.