MATH 637 - Mathematical Techniques in Data Science

Credit(s): 3

MATH TECHNIQUES IN DATA SCI
Component: Lecture
Linear methods for regression (subset selection, ridge, lasso), Logistic regression. Analysis of the convergence and complexity of common algorithms. Linear discriminant analysis, Principal component analysis, Additive Models, Kernel Smoothing. Cross-validation, Bootstrap, Support Vector Machines, Cluster analysis (K-means, spectral clustering), Undirected graphical models, Expectation maximization algorithm, Introduction to deep learning, Introduction to Bayesian methods.
Repeatable for Credit: N Allowed Units: 3 Multiple Term Enrollment: N Grading Basis: Student Option
PREREQ: Probability theory and basic statistics (e.g. MATH 350), Multivariable calculus (e.g. MATH 243), Linear Algebra (e.g. MATH 349), Optimization background (e.g. MATH 529) desirable but not necessary, basic computing skills.

Course Typically Offered: Spring