Optical Tech Would Update a Robot’s AI on the Fly

IEEE Spectrum · 2 months ago · 12

Cornell Tech researchers developed an optical receiver that uses light beams to directly update AI model parameters in processor memory, eliminating the need for power-hungry analog circuits. The prototype transmits data as QR-code-like light patterns at rates up to gigabits per second, with initial applications in edge AI systems like warehouse robots. If the approach overcomes current challenges with cell size and speed, it could reduce energy consumption in AI chips by avoiding traditional electrical memory transfers.