NEUR 182 SC - Machine Learning Using Neural Signals

This course teaches students the theory and practice of computational analyses of machine learning applied to neural signals for cognitive and neural classification. We will use real neural signals (e.g., spikes, EEG data, fMRI data, diffusion MRI data) in Python, Matlab, and R, so some computer programming experience is required (e.g., BIOL133L, PHYS108, PSYC123L, or equivalent). In this course, students will receive an overview of machine learning theory, an introduction to the concepts and practices of primary machine learning algorithms, and how to apply machine learning to information resulting from signal processing of neural signals. Each class meeting will involve theory and practical applications using active learning, giving students conceptual and computational capabilities that they can use for their own scholarly inquiry and computational applications.

Prerequisite(s): Prerequisites: Introduction to Computer Programming (preferably python or Matlab); Introduction to Probability and Statistics OR Calculus 2; Linear Algebra
Course Credit: 1.0
Offered: Every year

Please refer to the course schedule on the Scripps Portal for current course offerings and details.