Date(s) - 01/28/2021
4:30 pm - 5:30 pm

Please use this zoom link for the event.

Please join us for a UW Data Science Seminar event on Thursday, January 28th from 4:30 to 5:30 p.m. with Steven Peterson

“Towards naturalistic human neuroscience and neuroengineering”

Abstract: Understanding the neural basis of human movement has long been a key focus in neuroscience. However, researchers often study constrained, monotonous tasks that differ greatly from the rich and diverse natural movements that we actually make. In this talk, I will provide two examples of how my research has leveraged data science and machine learning to study neural oscillations during naturalistic human behavior. First, I will show how high-density electroencephalography (EEG) can be used to study neural activity during perturbed balance beam walking. By denoising and spatially localizing the EEG signal, I uncovered a common neural perturbation response that occurred in different cortical areas depending on the type of perturbation. Next, I will discuss how convolutional neural networks can be used to robustly decode intracranial neural activity pooled across multiple participants during unstructured arm movements. I will then wrap up with some exciting future directions in generalized neural decoding and unsupervised segmentation of large neural datasets. Overall, my research emphasizes the critical need to study naturalistic behaviors that mimic daily life and the important role that emerging data-driven approaches play in this endeavor.

Biography: Steven is a postdoctoral scholar co-advised by Bing Brunton and Raj Rao currently studying electrocorticography (ECoG) recordings during naturalistic movements. He received his Ph.D. in Biomedical Engineering at the University of Michigan, performing high-density electroencephalography (EEG) recordings during perturbed balance beam walking in the lab of Daniel Ferris. His interests are real-world neuroimaging, neural signal processing, and cortical integration of sensory information.

The UW Data Science Seminar is an annual lecture series at the University of Washington that hosts scholars working across applied areas of data science, such as the sciences, engineering, humanities and arts along with methodological areas in data science, such as computer science, applied math and statistics. Our presenters come from all domain fields and include occasional external speakers from regional partners, governmental agencies and industry.

All seminars will be hosted virtually for the 2020-2021 academic year, and are free and open to the public.