Assistant Professor & Viterbi Early Career Chair
Ming Hsieh Department of Electrical Engineering – Systems
Viterbi School of Engineering
University of Southern California
firstname.lastname@example.org Office: EEB408
10/24/2018 Our paper on multiscale decoding of spike-field activity is now published in Journal of Neural Engineering here.
10/11/2018 Our mood decoding paper is the cover article for the October issue of Nature Biotechnology here.
09/25/2018 DoD announces our new joint US-UK BARI program to build human-machine teams here.
09/17/2018 Our Journal of Neural Engineering paper on a computational framework for modeling the brain response to electrical stimulation is now published here.
09/10/2018 Our Nature Biotechnology paper on neural decoding of mood is now published here and the USC News Story is here. See also excerpts from Select Media Coverage: NewScientist, The Wall Street Journal, New Atlas
09/06/2018 We won the multi-institutional US-UK Bilateral Academic Research Initiative (BARI) award to work at the interface of AI and brain-machine interfaces.
06/29/2018 Watch Maryam’s invited lecture at the NAS Kavli Frontiers of Science on Brain-Machine Interfaces here
06/27/2018 Our research is featured in the IEEE’s The Institute publication here.
06/15/2018 IEEE Brain Initiative 2-part podcast series with Maryam Shanechi discussing brain-machine interfaces is now available here.
Our laboratory works at the interface of statistical inference and signal processing, machine learning, and control to develop algorithmic solutions for problems in basic and clinical neuroscience that involve the collection and manipulation of neural signals. Our work combines algorithm development and modeling with in vivo experimental implementation and testing, and is conducted in close collaboration with a variety of experimental labs. Some problems of interest include dynamic modeling of high-dimensional multiscale brain networks, decoding of cognitive or motor states from neural signals, developing closed-loop brain-machine interface (BMI) architectures for various applications, and devising closed-loop algorithms for control of neural signals using stimulation.
Some applications of interest include developing BMIs that aim to restore motor function in disabled patients. These BMIs record the neural activity in the relevant brain areas and use diverse mathematical tools to infer from this activity the motor intent of the user. We also develop BMIs for automatic closed-loop control of the brain state under anesthesia that adjust the real-time anesthetic infusion rate based on non-invasive neural recordings. Finally, we design BMIs for treatment of neuropsychiatric disorders that decode cognitive states and perform closed-loop brain stimulation.
Postdoctoral Position Available!