5th IBM IEEE CAS/EDS AI Compute Symposium (AICS’22)
5th IBM IEEE CAS/EDS AI Compute Symposium (AICS’22)
by Dr. Rajiv Joshi (IEEE Life Fellow), Kaoutar El Maghraoui, Arvind Kumar, Matthew Ziegler
T. J. Watson Research Center, Yorktown Heights, NY 10598
The 5th IBM IEEE CAS/EDS AI Compute Symposium, known as (AICS’22), was held for two days (11-12 Oct 2022) at the IBM T. J. Watson Research Center. The symposium was also supported by the IBM Academy of Technology
(https://www.ibm.com/blogs/academy-of-technology/). Dr. Joshi was the interface for CAS and EDS in organizing this successful event. The theme of the symposium was “Scalability to Sustainability”. In short, the symposium covered a range of topics from device technology, to circuits, architecture, algorithms, and sustainability to make innovations for the cloud with an emphasis on green AI.
For the third straight year, the symposium provided a virtual access option, allowing an increase in attendance. The event was very well attended and received great responses from the audience all over the world. Close to 1000 viewers for two days, participation from 50 countries, over 30 student posters, best poster awards, excellent panel discussions, and 11 distinguished speakers from industry and academia were the salient features of this symposium. There were more than 2600 views on the LinkedIn post about the symposium.
At the beginning, Dr. Rajiv Joshi, lead organizer, and IEEE Life Fellow gave welcoming remarks, a short history, progress, and the impact of the symposium.
Then Robert Muchsel, Analog Devices fellow, opened the symposium with an excellent presentation related to “Improving Privacy and Energy Usage by Pushing AI Inference to the Edge of the IoT Frontier”. Although artificial intelligence dominates the tech news, most AI solutions are expensive, big, and energy hungry. The connected nature of these systems also leads to significant concerns relating to privacy and system autonomy. Mr. Muchsel described ADI’s true edge AI accelerators, which employ many low-power innovations to enable AI inference on a battery while improving privacy through local computing at the edge.