Curriculum Core

Machine Learning PhD students will be required to complete courses in five different areas: Mathematical Foundations, Intermediate Statistics, ML Theory and Methods, Data Models, and Optimization.  With the exception of the Foundations and Data Models course, the requirements can be met with different courses in different schools.

 

Mathematical Foundations of Machine Learning.  This required course is the gateway into the program, and covers the key subjects from applied mathematics needed for a rigorous graduate program in ML. Particular emphasis will be put on advanced concepts in linear algebra and probabilistic modeling. This course will be cross-listed between CS, ECE, ISyE, and BMED.

 

Intermediate Statistics.  The purpose of this requirement is to expose students to the main concepts in mathematical statistics.  It can be met through any one of the three courses listed below.  While these courses emphasize different material, they are all centered on mathematical analysis of fundamental problems in statistics.

ISYE 6412, Theoretical Statistics

ECE 7251, Signal Detection and Estimation

MATH 6262, Statistical Estimation

 

Machine Learning Theory and Methods.  This course serves as an introduction to the foundational problems, algorithms, and modeling techniques in machine learning.  Each of the courses listed below treats roughly the same material using a mix of applied mathematics and computer science, and each has a different balance between the two.  

CS 7616, Pattern Recognition

CSE/ISYE 6740, Computational Data Analysis

ECE 6254, Statistical Machine Learning

ECE 6273, Methods of Pattern Recognition with Applications to Voice

 

Probabilistic Graphical Models. This course is cross-listed between the Schools of Computer Science, ISyE, and ECE. The course provides students with an introduction to the theory and practice of graphical models, one of the most important frameworks in machine learning and artificial intelligence.  

 

Optimization:  Optimization plays a crucial role in both developing new machine learning algorithms and analyzing their performance.  The three courses below all provide a rigorous introduction to this topic; each emphasizes different material and provides a unique balance of mathematics and algorithms.

ECE 8823, Convex Optimization: Theory, Algorithms, and Applications

ISYE 6661, Linear Optimization

ISYE 6663, Nonlinear Optimization

ISYE 6669,  Deterministic Optimization

ISYE 7683, Advanced Nonlinear Programming