Academics

  /  

Courses

  /  

Descriptions

COMP_SCI 396: Fairness in ML

VIEW ALL COURSE TIMES AND SESSIONS

Prerequisites

Permission of Instructor

Description

As machine learning (ML) models become more widely used in financial, healthcare, and
other high-stakes settings, concerns of models’ fairness become more important. While there are many
diGerent philosophical perspectives and mathematical measures of model behavior, there is no single
definition of fairness that can be applied to all models, tasks, or datasets. We will draw on research from
a wide variety of areas both within and outside computer science to evaluate and improve the fairness of
machine learning models. We will collectively work to create, evaluate, and critique an ML autograder
that can grade students’ written work. Syllabus
This class assumes prior knowledge of machine learning (e.g., COMP_SCI 349) and enrollment is by
permission only.

• This course fulfills the Technical Elective area.

REFERENCE TEXTBOOKS: None
REQUIRED TEXTBOOK: None
COURSE COORDINATORS: Zach Wood-Doughty
COURSE INSTRUCTOR: Prof. Zach Wood-Doughty