Dr. Yogatheesan Varatharajah, Research Assistant Professor in bioengineering at the University of Illinois at Urbana-Champaign, will give a presentation during the CAII Seminar Series on Monday, September 27 at 11:00 a.m. The talk is titled “Domain-guided Machine Learning for Health Analytics."
View Seminar here: https://go.ncsa.illinois.edu/2021CAIIFallSeminarSeries
Abstract: The utility of supervised machine learning in neurological applications has been limited because of the lack of large, labeled datasets. This is particularly emphasized in the applications that involve physiological time-series data such as EEG or PSG. At present, the labeling process is predominantly manual, and the pace of manual expert labeling cannot match the amount of clinical and research data being collected. To address this limitation, there has been a recent shift in focus towards physiology-inspired/domain-guided machine learning methods. The key idea is to utilize domain knowledge and labeled data as complementary means of supervision when designing and training machine learning models. In this talk, I will present some real-world examples of domain-guided machine learning applied to neurological diseases and discuss models built on top of core machine learning concepts such as graphical models, deep learning, and self-supervised learning.
Yogatheesan Varatharajah received his bachelor’s degree (2013) at the University of Moratuwa in Sri Lanka and his MS (2015) and Ph.D. (2020) degrees at the University of Illinois at Urbana-Champaign in Electrical and Computer Engineering. He was the recipient of an inaugural Mayo Clinic Illinois Alliance Fellowship, a Rambus Computer Engineering Fellowship, and an American Epilepsy Society Young Investigator Award. He is currently a Research Assistant Professor in the Department of Bioengineering at the University of Illinois at Urbana-Champaign with secondary affiliations with the Department of Electrical and Computer Engineering, Mayo Clinic Neurology, and the National Center for Supercomputing Architectures. His research is funded by the National Science Foundation and the Mayo Clinic Artificial Intelligence in Neurology program.
All presentations will be recorded and will be available on the CAII website shortly after the presentation.