Thursday, April 8, 2021 -
Communicating with brains directly is among the most thrilling technological advancements in our era. Recent brain-machine interface (BMI) studies have made substantial progress on acquiring and decoding neural signals. However, sending signals back to brains, e.g. encoding and modulating neural activities, remains a significant challenge. This talk discusses how this challenge can be addressed by intelligent, integrated, invasive (I3) BMI design. Specifically, I will present innovative mixed-signal integrated circuits (IC) and system design with edge machine learning for sensory encoding and therapeutic intervention of neurological disorders. Novel pre-clinical experiments in freely behaving animals enabled by the I3 BMI will be discussed. This technology holds great promise in improving millions of patients’ quality of life. The research outcomes have broader impacts on digital healthcare and artificial intelligence of things (AIoT). I will conclude this talk with my vision and future research plans to continue advancing the frontiers of BMI and IC technologies.
Dr. Xilin Liu received his Ph.D. from the University of Pennsylvania in 2017. He joined Qualcomm after graduation. His research interests include mixed-signal IC and system design with edge machine learning, especially for brain-machine interfaces. He has published papers on Nature Electronics, PNAS, top-tier IEEE transactions, etc. His first-author papers have received 3 Best Paper Awards at top conferences. He received a number of awards including the Solid-State Circuits Society (SSCS) Predoctoral Achievement Award in 2016 and Qualcomm Star Award in 2020. His industrial experience includes contributions to premium IC products including the world’s first commercial 5G chipset.