Photonic integrated circuits offer a promising platform for ultra-low-energy artificial intelligence computation, but their scalability is limited by the accumulation of analog hardware imperfections such as thermal crosstalk, phase noise, and digital-to-analog precision limits. Here we present a hardware–software co-designed framework enabling deep photonic neural computation on a single metasurface. A compact physics-informed neural network (PINN) trained through teacher–student distillation actively compensates thermal and quantization errors in programmable photonic meshes, restoring classification accuracy from 41.73% to 95.27% and achieving an extinction ratio of 63.96 dB. Building on this calibrated substrate, we introduce the Single-Layer Photonic Computing (SLiM) architecture that implements deep neural networks through temporal recurrence rather than spatial cascades. Using dual-wavelength differential detection to enable signed optical weights, the system emulates a 100-layer neural network on a single metasurface while achieving 95.20% MNIST classification accuracy and operating at 16.2 fJ per multiply-accumulate operation. These results demonstrate a scalable pathway toward fault-tolerant and energy-efficient photonic neural accelerators.
Building similarity graph...
Analyzing shared references across papers
Loading...
Ravi Raja Ramisetty
gopi chand kudipudi
Anvith Aravapalli
Nvidia (United States)
Nvidia (United Kingdom)
Koneru Lakshmaiah Education Foundation
Building similarity graph...
Analyzing shared references across papers
Loading...
Ramisetty et al. (Sun,) studied this question.
www.synapsesocial.com/papers/69ba428e4e9516ffd37a2d9f — DOI: https://doi.org/10.5281/zenodo.19045323