The Goergen Institute for Data Science welcomes distinguished lecturer Jack Gallant. This seminar is supported by the National Science Foundation Research Traineeship Data Enabled Science and Engineering (NRT-DESE) Award for Graduate Training in Data-Enabled Research into Human Behavior and Its Cognitive and Neural Mechanisms.
Title: Individualized High-Resolution Functional Mapping of the Human Brain Demonstrates the Power of Data Science
Abstract: Modern neuroimaging methods such as magnetic resonance imaging (fMRI) provide powerful tools for functional mapping of the human brain. However, the classical approach to neuroimaging is optimized for point-null hypothesis testing at the group level. This approach does not produce clear and verifiable measures of model prediction accuracy or generalization, and it does not provide much detailed information about functional maps in individuals. We have pioneered a new approach to neuroimaging that provides detailed high-dimensional functional maps of each individual's brain, and under complex, naturalistic conditions. Our methods also provide simple metrics of model prediction accuracy and generalization, and a generative link between individuals and the group. In this talk I will review our approach and its relationship to standard methods used in data science and machine learning, and provide several specific examples that illustrate the power of the approach.
Bio: Jack Gallant is a Chancellor's Professor and Class of 1940 Chair at the University of California at Berkeley. His primary appointment is in the Departments of Psychology and he is affiliated with the Department of Electrical Engineering and Computer Science, along with the programs in Bioengineering, Biophysics, Neuroscience and Vision Science. He received his Ph.D. from Yale University and did post-doctoral work at the California Institute of Technology and Washington University Medical School. His research program focuses on computational modeling of human brain activity. Further information about ongoing work, links to talks and papers and links to an online interactive brain viewer can be found at the lab web page.
Friday, September 13, 2019 at 11:00am to 12:00pm
Wegmans Hall, Auditorium 1400
250 Hutchison Rd, Rochester, NY 14620