Few-Shot Neuromorphic Vision in a Nonlinear Photonic Network Laser

TL;DR

This paper presents a neuromorphic photonic network inspired by biological retina mechanisms, capable of few-shot learning and high accuracy in image classification and segmentation tasks, outperforming traditional CNNs in low-data regimes.

Contribution

Introducing a silicon-compatible, nonlinear photonic network with heterogeneous inhibitory and excitatory dynamics for efficient few-shot learning and image analysis.

Findings

Achieved over 98% accuracy on MNIST

Outperformed EfficientNetV2 and ViT in few-shot regimes

Demonstrated effective segmentation on skin lesion dataset

Abstract

With the growing prevalence of AI, demand increases for hardware that mimics the brain's ability to extract structure from limited data. In the retina, ganglion cells detect features from sparse inputs via lateral inhibition, where neurons antagonistically suppress activity of neighbouring cells. Biological neurons exhibit diverse heterogeneous nonlinear responses, linked to robust learning and strong performance in low-data regimes. Here, we introduce a retinally-inspired photonic computing system where spatially-competing lasing modes in a random network laser act as heterogeneous, inhibitively-coupled neurons - enabling feature detection, few-shot classification, and segmentation. This silicon-compatible scheme harnesses heterogeneous excitatory and inhibitory nonlinear physical dynamics which give rise to emergent photonic computing behaviour, including parallel feature detection and strong performance when training data is scarce. We report 98.05% and 87.85% accuracy on MNIST and Fashion-MNIST, and 90.12% on BreaKHis cancer diagnosis - outperforming software CNNs including EfficientNetV2 and the vision transformer ViT in few-shot and class-imbalanced regimes with training sets of up to several hundred images. We demonstrate combined segmentation and classification on the HAM10k skin lesion dataset, achieving DICE and Jaccard scores of 84.49% and 74.80%. These results demonstrate the potential of random lasing networks as nonlinear photonic learning systems, and highlight the ability of heterogeneous nonlinear dynamics to support strong learning in challenging low-data scenarios.