Optical Spiking Neural Networks via Rogue-Wave Statistics

TL;DR

This paper introduces an optical spiking neural network leveraging rogue-wave statistics for nonlinear activation, enabling energy-efficient neuromorphic inference with competitive accuracy on image datasets.

Contribution

It presents a novel optical spiking neural network that uses rogue-wave phenomena for thresholding, combining physics-informed design and experimental validation.

Findings

Achieved 82.45% accuracy on BreastMNIST

Achieved 95.00% accuracy on Olivetti Faces

Demonstrated energy-efficient, scalable optical neural inference

Abstract

Optical computing could reduce the energy cost of artificial intelligence by leveraging the parallelism and propagation speed of light. However, implementing nonlinear activation, essential for machine learning, remains challenging in low-power optical systems dominated by linear wave physics. Here, we introduce an optical spiking neural network that uses optical rogue-wave statistics as a programmable firing mechanism. By establishing a homomorphism between free-space diffraction and neuronal integration, we demonstrate that phase-engineered caustics enable robust, passive thresholding: sparse spatial spikes emerge when the local intensity exceeds a significant-intensity rogue-wave criterion. Using a physics-informed digital twin, we optimize granular phase masks to deterministically concentrate energy into targeted detector regions, enabling end-to-end co-design of the optical transformation and a lightweight electronic readout. We experimentally validate the approach on BreastMNIST and Olivetti Faces, achieving accuracies of 82.45\% and 95.00\%, respectively, competitive with standard digital baselines. These results demonstrate that extreme-wave phenomena, often treated as deleterious fluctuations, can be harnessed as structural nonlinearity for scalable, energy-efficient neuromorphic photonic inference.