MACHINE LEARNING AND SIGNAL PROCESSING FOR NEURO ENGINEERING

Credit Hours: 3 · Undergraduate Upper-Level

This course covers signal processing and machine learning approaches for modern neuroscience data. Topics include latent variable models, point processes, dimensionality reduction, dynamical systems, and spectral analysis. Neuroscience applications include modeling neural firing rates, spike sorting, encoding, decoding, and electrical stimulation. Students will be introduced to public toolboxes that implement these methods. Cross-list: ELEC 548 , BIOE 548 . Graduate/Undergraduate Equivalency: ELEC 548 . Recommended Prerequisite(s): ( MATH 354 OR MATH 355 OR CMOR 302 OR CMOR 303 ) AND ( ELEC 303 OR STAT 305 OR STAT 310 OR ECON 307 ) Mutually Exclusive: Cannot register for ELEC 483 if student has credit for ELEC 548 .