Term: Fall 09
Course No.: 598-002
Credit Hours: 3
Instructor: Zeeshan Syed
Prerequisites: Stat 412 or IOE 265; MATH 216; Experience with MATLAB; or graduate standing
Explores modern machine learning in the context of real-world medical applications. Introduces students to different learning and feature extraction techniques for physiological data, and develops intuition on how these methods can be used to solve hard clinical problems in disease diagnosis, prevention and management. Topics covered include time-frequency analysis, non-linear dynamics, supervised and unsupervised learning, and symbolic analysis; with clinical applications from cardiology, neuroscience, obstetrics, oncology, surgery and intensive care monitoring. Focus on extensive hands-on experience with actual clinical data. Students expected to complete a final project using the methods learned in the course.
Target audience: Graduate students or advanced engineering undergraduates interested in healthcare applications. No prior experience in either machine learning or medicine is required, but basic knowledge of probability and statistics is assumed.
Lectures: TTH 12-1:30
Related Topics: Lab-Artificial Intelligence