Optical Tech Would Update a Robot’s AI on the Fly
IEEE Spectrum AI Alex Music
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.
Why it matters
Atop a lab bench, Cornell Tech postdoctoral researcher Yifan He positions the lens of an optical receiver almost a meter away from an LED emitting a beam of red light. The computer monitor attached to the receiver takes a beat to refresh, then displays an array of squares that resemble a QR code.When you hold your phone camera up to a QR code, light strikes the image sensor as only a first step to revealing the data hidden behind the black and white matrix. The receiver here is doing something different: Directly altering its own memory using the photocurrents produced by the beamed array of light. And unlike the data behind a QR code, which might point to a simple web address, this optical code could convey the parameters of an AI model. The new receiver design, presented last month at the IEEE/JSAP Symposium on VLSI Technology & Circuits, seeks to reduce the burden of increasing memory demands on AI systems. Shining data down onto processors could lower the energy typically required
