All-optical temporal integration mediated by subwavelength heat antennas
By: Yi Zhang , Nikolaos Farmakidis , Ioannis Roumpos and more
Potential Business Impact:
Makes computers process huge amounts of information super fast.
Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern artificial intelligence. We demonstrate an all-optical neuromorphic computing system based on time division multiplexing, capable of processing input vectors exceeding 250,000 elements within a unified framework. The platform harnesses optically driven thermo-optic modulation in standing wave optical fields, with titanium nano-antennas functioning as wavelength-selective absorbers. Counterintuitively, the thermal time dynamics of the system enable simultaneous time integration of ultra-fast (50GHz) signals and the application of programmable, non-linear activation functions, entirely within the optical domain. This unified framework constitutes a leap towards large-scale photonic computing that satisfies the dimensional requirements of AI workloads.
Similar Papers
A fully-programmable integrated photonic processor for both domain-specific and general-purpose computing
Optics
Computers use light to solve hard problems faster.
A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser
Optics
Makes AI faster and use less power.
Versatile silicon integrated photonic processor: a reconfigurable solution for next-generation AI clusters
Optics
Chip does many jobs for smart computers.