NE 412

Credit: 3 hours.

Modern technologies for recording brain activity hold the potential to enable a range of applications in neurology, neurobiology, and neuroscience in general. However, those recording technologies generate data at such scale and complexity that rigorous data analysis approaches for automatic information retrieval are required to fully leverage their potential. This course will introduce students to multiple neural data modalities (e.g., EEG and fMRI) and illustrate through examples, how modern data analysis techniques such as machine learning can be used to automatically extract meaningful information from those data. We will cover basics of neural data acquisition, preprocessing methods, data representation, dimensionality reduction, clustering, supervised learning, unsupervised learning, and some select advanced analytic concepts. This course will put equal emphasis on the understanding of analytical methods as well as practical hands-on experience, and equip the students with the essential skills to analyze neural data using advanced data analysis techniques such as machine learning. This course is designed for junior/senior undergraduate students with no or very limited prior experience in data science. Although prior exposure to the Python programming language is preferred, it is not required.

3 undergraduate hours. No graduate credit. Prerequisite: BIOE 210, BIOE 310, or instructor consent.