Math in Machine Learning

Catalog description

The goal of this topic course is to provide students with essential mathematical background for future practice and study in the field of data sciences and machine learning, including modern deep learning architecture. The course is organized as along the following three major themes: (1) Dimensionality Reduction and Transforms, which focus on Singular Value Decomposition (SVD) and Fourier Transform; (2) Machine Learning and Data Analysis, which includes Regression and Model Selection, Clustering and Classification, and Neural Networks; and (3) Dynamic Mode Decomposition. These themes represents important mathematical tools for machine learning and data analysis. In this course, students are also expected to review fundamental concepts in mathematics for machine learning and data sciences, including linear algebra, vector differential calculus, basic probability and optimization. Additionally, students will learn basic Python scripting and how to set up machine learning and deep learning environments for practical applications. Prereq: ( MATH 224 or MATH 228 ) and ( MATH 201 or MATH 307 ).