A groundbreaking new chip developed by engineers at the University of Pennsylvania utilizes light waves instead of electricity to perform complex mathematical operations crucial for training AI. This innovative chip has the potential to significantly boost computer processing speed and reduce energy consumption.
The use of light waves to interact with matter offers a promising path for creating computers that surpass the limitations of current chips, which are based on principles dating back to the early days of computing in the 1960s.
Published in Nature Photonics, the paper details the development of this revolutionary chip by Engheta’s group and Firooz Aflatouni, Associate Professor in Electrical and Systems Engineering.
Engheta explains, “We decided to collaborate, taking advantage of Aflatouni’s pioneering work in nanoscale silicon devices.”
Their objective was to create a platform for performing vector-matrix multiplication, a fundamental mathematical operation crucial for the development and operation of neural networks, the computer architecture that drives today’s AI tools.
2024-02-17 18:00:04
Post from phys.org
