Artificial intelligence (AI) holds the potential to drive major technological breakthroughs, but its progress has been slowed by energy inefficiencies and data transfer bottlenecks. Now, researchers at Columbia Engineering have developed a promising solution: a 3D photonic-electronic platform that dramatically improves both energy efficiency and bandwidth density. These are key steps toward building faster, more capable AI hardware.
The work, published in Nature Photonics and led by Keren Bergman, Charles Batchelor Professor of Electrical Engineering, introduces a novel approach that combines photonics with advanced complementary metal-oxide-semiconductor (CMOS) electronics. This integration enables high-speed, energy-efficient data communication and directly tackles one of AI’s biggest hardware limitations: moving large amounts of data quickly without draining power.
To read more, click here.