ECE 471

Credit: 3 OR 4 hours.

Extracting insights from heterogeneous datasets to support decision-making is fundamental to modern applications. This course teaches students to engineer analysis workflows that use feature engineering, longitudinal machine learning methods, and validation to derive real‐world insights from data. Students gain hands‐on experience through lectures and labs and via three projects involving large-scale real‐world data from domains such as autonomous-vehicles, healthcare and trust. While each workflow is end‐to‐end, students will delve deeper into methods as the course progresses.

3 undergraduate hours. 4 graduate hours. Prerequisite: Basic probability and basic computer programming skills are essential. ECE 313 or CS 361. Prior exposure to basics of scripting languages (such as Python), knowledge of operating systems (e.g., ECE 391, or an equivalent course) is beneficial.