Caltech Home > PMA Home > Calendar > Chen Institute Director's Seminar: Dr. Maryam...
open search form
Monday, February 02, 2026
11:00 AM - 12:00 PM
Chen 100

Chen Institute Director's Seminar: Dr. Maryam Shanechi

AI-driven neurotechnology for neural decoding and modulation
Maryam M. Shanechi, Alexander A. Sawchuk Endowed Chair and Professor of Electrical and Computer Engineering, Computer Science, Biomedical Engineering, and Neuroscience, USC,
Speaker's Bio:
Maryam M. Shanechi is the Alexander A. Sawchuk Endowed Chair and Professor of Electrical and Computer Engineering, Computer Science, Biomedical Engineering, and Neuroscience at USC, where she is also the Founding Director of the Center for Neurotechnology. She received her B.A.Sc. in Engineering Science from the University of Toronto and her S.M. and Ph.D. in Electrical Engineering and Computer Science from MIT. Her research integrates engineering, AI, and neuroscience to develop next-generation neurotechnologies and advance our understanding of the brain. Her honors include the NIH Director’s New Innovator Award, NSF CAREER Award, ONR Young Investigator Award, ASEE Curtis W. McGraw Research Award, MIT Technology Review Innovators Under 35 (TR35), Popular Science Brilliant 10, Science News SN10, One Mind Rising Star Award, and a DoD MURI. She is a Fellow of IEEE and AIMBE and a two-time Blavatnik National Awards Finalist.

Please join us for a Chen Institute Director's Seminar with speaker Dr. Maryam M. Shanechi, the Alexander A. Sawchuk Endowed Chair and Professor of Electrical and Computer Engineering, Computer Science, Biomedical Engineering, and Neuroscience at USC, where she is also the Founding Director of the Center for Neurotechnology.

Title: AI-driven neurotechnology for neural decoding and modulation

Abstract: A major challenge in neurotechnology and neuroAI is to model, decode, and modulate the activity of large-scale neural populations that underlie brain function and dysfunction. Toward addressing this challenge, I will present our work on novel dynamical modeling frameworks that characterize neural-behavioral data and enable a new generation of brain-computer interfaces for disorders such as major depression. First, I will introduce a framework that jointly describes neural and behavioral signals, dissociates behaviorally relevant neural dynamics, and decodes brain states such as mood from neural activity. I will then show how the framework can also predict the effects of inputs—such as sensory stimuli or neurostimulation—to disentangle intrinsic from input-driven neural dynamics. I will further illustrate how these models can integrate multimodal neural signals, including spikes, field potentials, and brain-wide neuroimaging. Finally, I will discuss the challenge of developing AI algorithms for neurotechnology and present methods that enable accurate, flexible inference of brain states and generalize across subjects. Together, these modeling frameworks can enable next-generation AI-driven neurotechnologies that restore lost motor and emotional function in diverse brain disorders such as paralysis and major depression.

For more information, please contact Chen Institute by email at [email protected].