Mathematical Foundations of Data Science

This course gives you the mathematical machinery behind modern machine learning, treating data science as an applied marriage of linear algebra and probability rather than a collection of recipes. You'll work through homeworks and a project that exercise SVD and low-rank approximation, concentration inequalities, regularized regression like Lasso, and the optimization (SGD, backprop) that actually trains neural nets. It sits at the senior/graduate boundary, leaning on linear algebra and probability prerequisites, and is what lets you read deep learning papers or take graduate statistics and optimization courses without treating the math as a black box.