Undergraduate Researchers Help Unlock Lessons of Machine Learning and AI – College of Natural Sciences

Brain-Machine Interface

AI also intersects with language in other research areas. Nihita Sarma, a computer sciencethird-year student and member of Deans Scholars and Turing Scholars, researches theintersection of neuroscience and machine learning to understand language in the brain, workingwith Michael Mauk, professor of neuroscience, and Alexander Huth, an assistant professor ofcomputer science and neuroscience.

As research subjects listen to podcasts, they lie in an MRI machine and readings track their brainactivity. These customized-to-the-subject readings are then used to train machine learningmodels called encoding models, and Sarma then passes them through decoding models.

My research is taking those encodings and trying to backtrack and figure out based on thisneural representation based on the brain activity that was going on at that moment whatcould the person inside the MRI machine possibly have been thinking or listening to at thatmoment? Sarma said.

Along with gaining a better understanding of how language is represented in the brain, Sarmasaid the research has possible applications for a noninvasive communication tactic for peopleunable to speak or sign.

We would be able to decode what theyre thinking or what theyre trying to say, and allow themto communicate with the outside world, Sarma said.

Read more here:
Undergraduate Researchers Help Unlock Lessons of Machine Learning and AI - College of Natural Sciences

Related Posts

Comments are closed.