Sensing & Machine Learning for Neural Interfaces

4 credits · College of Engineering catalogue

Advisory Prerequisite: None. Enforced Prerequisite: (BIOMEDE 211 or EECS 215 or EECS 314) and (EECS 216) and (MATH 216) and (ENGR 101 or EECS 183 or EECS 180 or EECS 280); No OP/F; or graduate standing. Minimum grade requirement of “B” for enforced prerequisite. (4 credits) Focuses on techniques for interfacing with the human nervous system to obtain control signals for assistive technologies. Students first implement quantitative models of neural recording and stimulation. Then students apply machine learning techniques to extract control signals from large neural datasets. This course has a flipped format with classtime dedicated to help with code implementation. Real datasets from brain machine interfaces and nerve/muscle controlled prostheses will be used throughout the course.