This document summarizes a course on mathematics for machine learning. The course covered topics like linear algebra, multivariate calculus, statistics, and optimization algorithms. The linear algebra modules covered vectors, operations on vectors, matrices, matrix multiplication, basis transformations, and eigenvectors/eigenvalues. The calculus modules generalized calculus tools to multivariate systems, covered the chain rule and its applications in neural networks, Taylor series, and optimization methods like gradient descent and Newton-Raphson. The document emphasizes that mathematics is crucial for machine learning as it provides the foundational toolkit and methods for tasks like data fitting, optimization, and modeling complex relationships in data.