Photonic Neuromorphic Computing enabled by a BIC Metasurface

TL;DR

This paper introduces a monolithic photonic recurrent network using a BIC metasurface that integrates nonlinearity, connectivity, and memory, enabling high-speed, energy-efficient neuromorphic computing with demonstrated benchmark task performance.

Contribution

It presents the first implementation of a reconfigurable, monolithic photonic recurrent network based on BIC metasurfaces with integrated nonlinearity and memory for neuromorphic computing.

Findings

Achieved 92.16% accuracy in MRI image classification.

Achieved 85.36% accuracy in human action recognition.

Validated the system on benchmark tasks.

Abstract

Photonic neuromorphic computing promises revolutionary advances in parallel and high-speed processing, yet a key challenge persists: co-integrating nonlinearity, dense connectivity, and intrinsic memory monolithically to enable brain-inspired, spatiotemporal information processing. Here, we overcome this challenge by introducing a monolithic photonic recurrent network based on an active metasurface operating at bound state in the continuum (BIC). The BIC mode mediates strong,long-range coupling across the lattice, creating a reconfigurable recurrent network topology in hardware. Concurrently, the gain medium provides both optical nonlinearity for neuronal activation and a finite carrier lifetime that serves as a built in, analog temporal memory. This synergy enables computation to emerge directly from the collective spatiotemporal dynamics of the driven-dissipative photonic system, effectively realizing a physical reservoir computer on a chip. We experimentally validate a minimal yet physically complete system on benchmark tasks: brain MRI image classification and human action recognition, achieving 92.16% and 85.36% accuracies, respectively. This work establishes a scalable pathway toward ultrafast, energy-efficient neuromorphic intelligence where processing is an inherent property of tailored light matter interaction.