Decoding Minds from Brain Scans

From mind uploading to brain in a jar, the ability to preserve and decode our minds has long been a fascination of science fiction. With fast improving brain-imaging technologies, that future is closer to scientific reality than you might think. In this part-lecture, part-tutorial, Science Workshop speaker Syed Fahad Sultan will talk about how to build machine learning classifiers on data from functional magnetic resonance imaging (fMRI) scans to predict the mental state of subjects and stimuli in the fMRI scanner. He will also talk about how he used such models in his research to predict disease, behavior, and other phenotypes from fMRI data collected during resting state. The talk will also include a brief discussion on reproducibility problems and other challenges with fMRI studies, as well as their potential applications in clinical diagnoses and brain-computer interfaces in the future.

Syed Fahad Sultan is a fifth-year Ph.D. candidate at Stony Brook University. Fahad's research focuses on using data science and machine learning towards building better predictive models and representations for large-scale neuroimaging and genetic datasets. Fresh out of college, Fahad worked as a video game developer and helped build TapFish, the top-grossing game worldwide on the App Store and Google Play for two weeks in 2011. Fahad has also worked at research labs in Pakistan and Saudi Arabia, working towards more inclusive technologies for marginalized communities and innovative urban sensing techniques for better crowd control during the largest human gathering in the world.