Skip to main content

140.644.01
Statistical Machine Learning: Methods, Theory, and Applications

Location
East Baltimore
Term
1st Term
Department
Biostatistics
Credit(s)
4
Academic Year
2024 - 2025
Instruction Method
In-person
Class Time(s)
Tu, Th, 1:30 - 2:50pm
Auditors Allowed
Yes, with instructor consent
Available to Undergraduate
No
Grading Restriction
Letter Grade or Pass/Fail
Course Instructor(s)
Contact Name
Frequency Schedule
Every Year
Prerequisite

Students are expected to be familiar with the following topics to comfortably complete this class: Linear Algebra, Intermediate Statistics, and Basic R. If you do not know these topics, it is your responsibility to do background reading to make sure you understand these concepts.

Description
Introduces statistical and computational foundations of modern statistical machine learning. Acquaints students with modern statistical machine learning models and their statistical and theoretical underpinnings. Includes topics: regression and classification, resampling methods (cross-validation and bootstrap), model and variable selection, tree-based methods for regression and classification, functional regression models, unsupervised learning, support vector machines, ensemble methods, deep learning, visualization of large datasets. Includes example applications of cancer prognosis from microarray data, graphical models for data visualization, and a prediction of survival using high-dimensional predictors.
Learning Objectives
Upon successfully completing this course, students will be able to:
  1. Identify the appropriate machine learning methods to address major scientific questions.
  2. Interpret the results obtained by the common machine learning methods
  3. Describe methods to evaluate and compare the performance of the machine learning models
  4. Implement all analyses and methods within R
Methods of Assessment
This course is evaluated as follows:
  • 50% Homework
  • 50% Final Project
Special Comments

Please note: This is the in-person section of a course that is also offered virtually/online. Students will need to commit to the modality for which they register.