Empowering the Next Billion Devices with Deep Learning

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 AI, in particular, deep learning, to edge devices to realize the vision of Artificial Intelligence of Things (AIoT).

This talk consists of two parts. The first part focuses on how we address some of the most fundamental problems that act as the key barriers of achieving the vision of AIoT. First, I will present our work on designing adaptive frameworks that empower AI-embedded edge devices to adapt to the inherently dynamic runtime system resources in real-world deployments. Second, I will present our work on distributed on-device training that enables heterogeneous edge devices to collaboratively train an AI model on the devices without leaking the private data to the cloud server. Third, I will talk about our work on developing automated machine learning (AutoML) frameworks that provide an automated and scalable solution to the device deluge challenge in AIoT. In the second part of this talk, I will present how we use AI as the core component to design AIoT systems for a broad range of problem domains. I will focus on one killer application of edge computing, and present an AI-empowered distributed edge system for low-latency, high-throughput, and scalable live video analytics. Finally, I will briefly talk about our award-winning mobile AI technologies that tackle some of the most important healthcare problems to improve the life quality of millions of people.

Bio:

Mi Zhang is an Associate Professor and the Director of Machine Learning Systems Lab at Michigan State University. He received his Ph.D. in Computer Engineering from University of Southern California and B.S. in Electrical Engineering from Peking University. Before joining MSU, he was a postdoctoral scholar at Cornell University. His research lies at the intersection of embedded systems and machine intelligence, spanning areas including on-device/edge AI for mobile/wearable/IoT/embedded sensor systems, TinyML, automated machine learning (AutoML), systems for machine learning, machine learning for systems, federated learning, and human-centered AI for health and social good. Dr. Zhang has received a number of awards for his research. He is the 4th Place Winner (1st Place in U.S. and Canada) of 2019 Google MicroNet Challenge (CIFAR-100 Track), the Third Place Winner of 2017 NSF Hearables Challenge, and the champion of 2016 NIH Pill Image Recognition Challenge. He is the recipient of seven best paper awards and nominations. He is also the recipient of the NSF CRII Award, Facebook Faculty Research Award, Amazon Machine Learning Research Award, and MSU Innovation of the Year Award. Many of his works have been reported by NSF, NIH, IEEE, ACM, and media such as TIME, MIT Technology Review, WIRED, TechCrunch, and Smithsonian magazine for more than one hundred times.