Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April 24, 2024
-
ECE Seminar: Dr. Yuejie Chi, "Solving Inverse Problems with Generative Priors: From Low-rank to Diffusion Models"
Wed, Apr 24, 2024 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Yuejie Chi, Sense of Wonder Group Endowed Professor in AI Systems | Department of Electrical and Computer Engineering | Carnegie Mellon University
Talk Title: Solving Inverse Problems with Generative Priors: From Low-rank to Diffusion Models
Abstract: Generative priors are effective countermeasures to combat the curse of dimensionality, and enable efficient learning and inversion that otherwise are ill-posed, in data science. This talk begins with the classical low-rank prior, and introduces scaled gradient descent (ScaledGD), a simple iterative approach to directly recover the low-rank factors for a wide range of matrix and tensor estimation tasks. ScaledGD provably converges linearly at a constant rate independent of the condition number at near-optimal sample complexities, while maintaining the low per-iteration cost of vanilla gradient descent, even when the rank is overspecified and the initialization is random. Going beyond low rank, the talk discusses diffusion models as an expressive data prior in inverse problems, and introduces a plug-and-play posterior sampling method (Diffusion PnP) that alternatively calls two samplers, a proximal consistency sampler solely based on the forward model, and a denoising diffusion sampler solely based on the score functions of data prior. Performance guarantees and numerical examples will be demonstrated to illustrate the promise.
Biography: Dr. Yuejie Chi is the Sense of Wonder Group Endowed Professor of Electrical and Computer Engineering in AI Systems at Carnegie Mellon University, with courtesy appointments in the Machine Learning department and CyLab. She received her Ph.D. and M.A. from Princeton University, and B. Eng. (Hon.) from Tsinghua University, all in Electrical Engineering. Her research interests lie in the theoretical and algorithmic foundations of data science, signal processing, machine learning and inverse problems, with applications in sensing, imaging, decision making, and generative AI. Among others, Dr. Chi is a recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE), the inaugural IEEE Signal Processing Society Early Career Technical Achievement Award for contributions to high-dimensional structured signal processing, and multiple paper awards including the SIAM Activity Group on Imaging Science Best Paper Prize and IEEE Signal Processing Society Young Author Best Paper Award. She is an IEEE Fellow (Class of 2023) for contributions to statistical signal processing with low-dimensional structures.
Host: Dr. Richard Leahy, leahy@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
AAI-CCI-MHI Seminar on CPS
Wed, Apr 24, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Rose Faghih, Associate Professor New York University
Talk Title: Smartwatch-Brain Interface Architectures for Mental Well-Being and Productivity
Series: EE598 Seminar Series
Abstract: Smartwatch-like wearables have enabled seamless tracking of vital signs and physical activities. An unexploited capability is that the pulsatile physiological time series collected by wrist-worn wearable devices can be used for recovering internal brain dynamics. We design algorithms for a closed-loop brain-aware wearable architecture called MINDWATCH for tracking and regulating neurobehavioral states of arousal and performance. This closed-loop smartwatch-brain interface framework includes (1) an inference engine for recovering arousal-related autonomic nervous system (ANS) activations, (2) Bayesian state-space decoders for tracking cognitive arousal and performance states, (3) control algorithms for maintaining these neurobehavioral states within desired ranges, and (4) neurofeedback experiments for closing the loop via safe actuation. The methods are validated by analyzing experimental data as well as simulation studies. Results demonstrate a promising approach for tracking and regulating neurocognitive arousal and performance states through wearable devices. Since smartwatches can be used conveniently in one’s daily life, smartwatch-brain interface architectures have a great potential to monitor and regulate one’s neurocognitive stress seamlessly in real-world situations.
Biography: Rose T. Faghih is an associate professor of Biomedical Engineering at the New York University (NYU) where she directs the Computational Medicine Laboratory within the NYU Langone Health's Tech4Health Institute. She received a bachelor’s degree (summa cum laude) in Electrical Engineering (Honors Program Citation) from the University of Maryland, and S.M. and Ph.D. degrees in Electrical Engineering and Computer Science with a minor in Mathematics from Massachusetts Institute of Technology (MIT). She completed her postdoctoral training at the Department of Brain and Cognitive Sciences and the Picower Institute for Learning and Memory at MIT as well as the Department of Anesthesia, Critical Care and Pain Medicine at the Massachusetts General Hospital. Rose is the recipient of various awards including a 2023 National Institutes of Health (NIH) Maximizing Investigators' Research Award for Early-Stage Investigators, a 2020 National Science Foundation CAREER Award, a 2020 MIT Technology Review Innovator Under 35 award, and a 2016 IEEE-USA New Face of Engineering award. In 2020, she was featured by the IEEE Women in Engineering Magazine as a “Woman to Watch”. She is on the editorial board of PNAS Nexus by the National Academy of Sciences and IEEE Transactions on Neural Systems and Rehabilitation Engineering. Her research interests include wearable technologies, and medical cyber-physical systems, as well as neural and biomedical signal processing.
Host: Pierluigi Nuzzo
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Ariana Perez
