IEEE Communication Society (ComSoc) Buenaventura/Coastal LA Chapters Distinguished Lecture (w/ Prof. Christopher Brinton)
This is a hybrid event hosted by IEEE Buenaventura and Coastal LA COMSOC Chapters. This talk by distinguished lecturer, Prof. Christopher Brinton will address an application of AI/ML in wireless networks.
Fog learning is an emerging paradigm for optimizing the orchestration of artificial intelligence services over contemporary network systems. Different from existing distributed techniques such as federated learning, fog learning emphasizes intrinsically in its design the unique node, network, and data properties encountered in today’s fog networks that span computing elements from the edge to the cloud. An important thread of research in fog learning has been on understanding the role that local topologies formed on an ad-hoc basis among proximal groups of heterogeneous computing elements can play in elevating the achievable tradeoff between intelligence quality and resource efficiency.
Date and Time
Location
Hosts
Registration
- Date: 28 Jan 2025
- Time: 12:00 PM to 01:00 PM
- All times are (UTC-08:00) Pacific Time (US & Canada)
- Add Event to Calendar
- 2310 E. El Segundo Blvd
- El Segundo, California
- United States 90245-4609
- Building: A2
- Click here for Map
- Starts 15 January 2025 12:00 AM
- Ends 24 January 2025 12:00 AM
- All times are (UTC-08:00) Pacific Time (US & Canada)
- No Admission Charge
Speakers
Christopher of Purdue University
From Federated to Fog Learning: Expanding the Frontier of Model Training over Contemporary Wireless Network Systems
Fog learning is an emerging paradigm for optimizing the orchestration of artificial intelligence services over contemporary network systems. Different from existing distributed techniques such as federated learning, fog learning emphasizes intrinsically in its design the unique node, network, and data properties encountered in today’s fog networks that span computing elements from the edge to the cloud. An important thread of research in fog learning has been on understanding the role that local topologies formed on an ad-hoc basis among proximal groups of heterogeneous computing elements can play in elevating the achievable tradeoff between intelligence quality and resource efficiency. In this talk, I will discuss recent results on the analysis of fog learning processes which give insights into the impact that these topologies, along with other properties such as model characteristics and fog decision parameters, have on global training performance. Additionally, I will discuss the development of adaptive control methodologies that leverage such relationships for jointly optimizing relevant fog learning metrics.
Biography:
Christopher G. Brinton is the Elmore Associate Professor of Electrical and Computer Engineering (ECE) at Purdue University. His research interest is at the intersection of networking, communications, and machine learning, specifically in fog/edge network intelligence, distributed machine learning, and AI/ML-inspired wireless network optimization. Dr. Brinton is a recipient of five of the US top early career awards, from the National Science Foundation (CAREER), Office of Naval Research (YIP), Defense Advanced Research Projects Agency (YFA and Director’s Fellowship), and Air Force Office of Scientific Research (YIP), the IEEE Communication Society William Bennett Prize Best Paper Award, the Intel Rising Star Faculty Award, the Qualcomm Faculty Award, and roughly $17M in sponsored research projects as a PI or co-PI. He has also been awarded Purdue College of Engineering Faculty Excellence Awards in Early Career Research, Early Career Teaching, and Online Learning. He currently serves as an Associate Editor for IEEE/ACM Transactions on Networking, and previously was an Associate Editor for IEEE Transactions on Wireless Communications. Prior to joining Purdue, Dr. Brinton was the Associate Director of the EDGE Lab and a Lecturer of Electrical Engineering at Princeton University. He also co-founded Zoomi Inc., a big data startup company that holds US Patents in machine learning for education. His book The Power of Networks: 6 Principles That Connect our Lives and associated Massive Open Online Courses (MOOCs) reached over 400,000 students. Dr. Brinton received the PhD (with honors) and MS Degrees from Princeton in 2016 and 2013, respectively, both in Electrical Engineering.
Agenda
11:45 pm - 12:00 pm - Networking & Food & Introductions
12:00 pm - 1:00 pm -Presentation and Q&A