Low-power multimode-fiber projector outperforms shallow-neural-network classifiers

In the domain of disordered photonics, the characterization of optically opaque materials for light manipulation and imaging is a primary aim. Among various complex devices, multimode optical fibers stand out as cost-effective and easy-to-handle tools, making them attractive for several tasks. In this context, we use these fibers as random hardware projectors, transforming an input dataset into a higher-dimensional speckled image set. The goal of our study is to demonstrate that using such randomized data for classification by training a single logistic regression layer improves accuracy compared to training on direct raw images. Interestingly, we found that the classification accuracy achieved is higher than that obtained with the standard transmission-matrix model, a widely accepted tool for describing light transmission through disordered devices. We conjecture that this improved performance could be due to the hardware classifier operating in a flatter region of the loss landscape when trained on fiber data, which aligns with the current theory of deep neural networks. These findings suggest that the class of random projections operated by multimode fibers generalize better to previously unseen data, positioning them as promising tools for optically assisted neural networks. With this study, we seek to contribute to advancing the knowledge and practical utilization of these versatile instruments, which may play a significant role in shaping the future of neuromorphic machine learning.