This two-week course covers the foundations of modern machine learning. Students begin with supervised learning fundamentals, including k-nearest neighbors, linear and logistic regression, perceptrons, and gradient descent. The course then progresses through support vector machines, kernel methods, Gaussian processes, and tree-based models including decision trees, random forests, and boosting. The second week shifts to neural networks, unsupervised learning (clustering, GMMs, PCA), and sampling, before concluding with contemporary topics: generative modeling and diffusion, transformers and large language models, and reinforcement learning