Conferences, Lectures, & Seminars
Events for December
-
Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute Seminar Series
Wed, Dec 01, 2021 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Mi Zhang , Machine Learning Systems Lab at Michigan State University
Talk Title: Empowering the Next Billion Devices with Deep Learning
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: The proliferation of edge devices and the gigantic amount of data they generate make it no longer feasible to transmit all the data to the cloud for processing. Such constraints fuel the need to move the intelligence from the cloud to the edge where data reside. In this talk, I will present our works on how we bring the power of deep learning to edge devices to realize the vision of Artificial Intelligence of Things (AIoT).
First, I will present our work on designing adaptive frameworks that empower AI-embedded edge devices to adapt to the inherently dynamic runtime resources to enable elastic on-device AI. Second, we shift from the single edge device setting to the distributed setting for the task of distributed on-device inference. I will focus on one killer application of edge computing, and present a distributed workload-adaptive framework for low-latency high-throughput large-scale live video analytics. Third, I will present our work on designing a distributed on-device training framework that significantly enhances the on-device training efficiency without compromising the training quality. Lastly, I will talk about our work on developing automated machine learning (AutoML) techniques to address the device deluge challenge which acts as one key barrier of achieving the vision of AIoT.
Biography: Mi Zhang is an Associate Professor and the Director of the Machine Learning Systems Lab at Michigan State University. He received his Ph.D. from University of Southern California and B.S. from Peking University. Before joining MSU, he was a postdoctoral scholar at Cornell University. His research lies at the intersection of mobile/edge/IoT systems and machine intelligence, spanning areas including On-Device/Edge AI, Automated Machine Learning (AutoML), Federated Learning, Systems for Machine Learning, Machine Learning for Systems, and AI for Health and Social Good. He has received a number of awards for his research. He is the 4th Place Winner of the 2019 Google MicroNet Challenge, the Third Place Winner of the 2017 NSF Hearables Challenge, and the champion of the 2016 NIH Pill Image Recognition Challenge. He is the recipient of seven best paper awards and nominations. He is also the recipient of the National Science Foundation CRII Award, Facebook Faculty Research Award, Amazon Machine Learning Research Award, and MSU Innovation of the Year Award.
Host: Pierluigi Nuzzo and Bhaskar Krishnamachari
Webcast: https://usc.zoom.us/webinar/register/WN_p5OEJlPxQlakO4hqovuGEQLocation: Online
WebCast Link: https://usc.zoom.us/webinar/register/WN_p5OEJlPxQlakO4hqovuGEQ
Audiences: Everyone Is Invited
Contact: Talyia White
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Ming Hsieh Institute Seminar Series on Integrated Systems
Fri, Dec 03, 2021 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jie Gu, Associate Professor, Northwestern University
Talk Title: Exploring New Dimensions of CMOS Deep Learning Accelerators with Neural CPU Architecture and Compute-in-Memory Circuits
Host: Mike Chen, Hossein Hashemi, Manuel Monge, Constantine Sideris
More Information: MHI IS Seminar - Jie Gu_Flyer.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Jenny Lin
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Medical Imaging Seminar Series
Fri, Dec 10, 2021 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Talk Title: Improved Regularized Simultaneous Multi-slice (SMS) Imaging Reconstruction
Series: Medical Imaging Seminar Series
Abstract: MRI acquisitions are inherently slow, necessitating the use of accelerated imaging. Simultaneous multi- slice (SMS) imaging has gained substantial interest by providing improved coverage with minimum signal- to-noise ratio (SNR) loss in accelerated MRI and has been widely integrated into large-scale projects such as Human Connectome Project. However, ultra-high accelerations are prone to noise amplification and residual aliasing artifacts, necessitating new reconstruction techniques that can successfully suppress both. In this talk, we will present recently developed techniques for regularized SMS reconstruction. We will first introduce two model-based algorithms that simultaneously reduce noise amplification and inter-leakage artifacts. Subsequently, we will concentrate on physics-guided deep learning reconstruction for SMS MRI with applications in fMRI. Finally, we will discuss an alternative way to view the multi-coil encoding operator in physics-guided DL reconstruction for improved generalizability in dynamic contrast-enhanced MRI.
Biography: Omer Burak Demirel is a PhD candidate at the University of Minnesota working with Prof. Mehmet Akçakaya. Prior to the University of Minnesota, he received the B.S. and M.S. degrees from Bilkent University, Ankara, Turkey in January 2015 and June 2017, respectively. His research interests include image processing, MRI acquisition methods, image reconstruction techniques and accelerated MRI. He is a recipient of an AHA predoctoral fellowship focusing on improved image reconstruction techniques for cardiac MRI.
Host: Krishna Nayak, knayak@usc.edu
Webcast: https://usc.zoom.us/j/95249648177?pwd=RHNsSnlhMk0vaEtPeExXRkRPOE55dz09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
WebCast Link: https://usc.zoom.us/j/95249648177?pwd=RHNsSnlhMk0vaEtPeExXRkRPOE55dz09
Audiences: Everyone Is Invited
Contact: Talyia White
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
