Few-shot neuromorphic vision in a nonlinear photonic network laser
File(s)
Published version
Author(s)
Type
Journal Article
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.
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.
Date Issued
2026-09-04
Date Acceptance
2026-07-22
Citation
Science Advances, 2026, 12 (36)
ISSN
2375-2548
Publisher
American Association for the Advancement of Science (AAAS)
Journal / Book Title
Science Advances
Volume
12
Issue
36
Copyright Statement
© 2026 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY). https://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
License URL
Publication Status
Published
Date Publish Online
2026-09-04