Part I: Foundations
The mathematical foundations of machine learning: regression, classification, neural networks, and gradient-based optimization.
Linear Regression & Regularization
OLS, ridge, LASSO, bias-variance tradeoff
Classification & Logistic Regression
Decision boundaries, softmax, cross-entropy
Neural Networks
Universal approximation, activation functions, architecture
Backpropagation & Optimization
Chain rule, SGD, Adam, learning rate schedules