Dr. Shanechi will present our work at the interface of AI/ML and neuroscience to develop next-generation brain-computer interfaces that can model, decode, and modulate the activity of large populations of neurons in brain disorders such as major depression. First, I present a dynamical modeling framework that can decode brain states such as mood from human brain network activity. Then, I show how we can also predict the effect of external inputs, such as electrical stimulation, on brain network activity toward closed-loop modulation of neural states. I also develop a novel dynamical modeling framework to jointly describe neural-behavioral data and dissociate behaviorally relevant neural dynamics. I then extend these models to admit multiple neural modalities and enable multimodal fusion. Finally, I discuss the challenge of developing AI algorithms for real-time neurotechnology. I will present a framework that combines neural networks with stochastic state-space models to enable accurate yet flexible inference of brain states causally, non-causally, and even with missing neural samples. These AI-based neurotechnologies can help restore lost motor and emotional function in millions of patients with brain disorders.
Refreshments will be provided to in-person attendees.
