Ahmed Louri, the David and Marilyn Karlgaard Professor of Electrical and Computer Engineering, and his students have received two new patents for innovative artificial intelligence accelerator designs.
The first patent, developed with GW student Jiajun Li, introduces a scalable architecture to improve the speed and efficiency of graph-based AI models used in applications such as recommendation systems, e-commerce analysis and drug discovery.
The second patent, developed with GW students Jiaqi Yang and Hao Zheng, enables multiple deep neural networks to run simultaneously through optimized memory access, adaptive communication systems and intelligent scheduling.
These innovations build on Louri’s broader research into next-generation computing architectures, including prior patented work focused on optimizing and securing on-chip communication. To date, Louri holds patents from the U.S. Patent and Trademark Office related to AI and advanced computing technologies, reinforcing his leadership in the field.