# Low-power multi-mode fiber projector overcomes shallow neural networks classifiers

arXiv: https://arxiv.org/abs/2210.04745 · HTML: https://mlsanity.com/paper/2210.04745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 10 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Generalisation error in learning with random features and the hidden manifold model](https://mlsanity.com/paper/2002.09339/) (2020)
- [The Gaussian equivalence of generative models for learning with shallow neural networks](https://mlsanity.com/paper/2006.14709/) (2020)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes](https://mlsanity.com/paper/1605.06444/) (2016)
- [Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses](https://mlsanity.com/paper/1509.05753/) (2015)
- [An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition](https://mlsanity.com/paper/2008.10400/) (2020)
- [Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks](https://mlsanity.com/paper/1909.06553/) (2019)
- [Entropic gradient descent algorithms and wide flat minima](https://mlsanity.com/paper/2006.07897/) (2020)
- [Learning through atypical "phase transitions" in overparameterized neural networks](https://mlsanity.com/paper/2110.00683/) (2021)
- [Scalable Optical Learning Operator](https://mlsanity.com/paper/2012.12404/) (2020)
- [Random Projections through multiple optical scattering: Approximating kernels at the speed of light](https://mlsanity.com/paper/1510.06664/) (2015)
- [Hybrid training of optical neural networks](https://mlsanity.com/paper/2203.11207/) (2022)
- [A complete, parallel and autonomous photonic neural network in a semiconductor multimode laser](https://mlsanity.com/paper/2012.11153/) (2020)
- [Classification of time-domain waveforms using a speckle-based optical reservoir computer](https://mlsanity.com/paper/1909.12489/) (2019)
- [Transmission Matrix Inference via Pseudolikelihood Decimation](https://mlsanity.com/paper/1903.05379/) (2019)

## Abstract (arXiv)

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, multi-mode optical fibers stand out as cost-effective and easy-to-handle tools, making them attractive for several tasks. In this context, we cast these fibers into 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 the reason for such improved performance could be due to the fact that the hardware classifier operates 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 multi-mode fibers generalize better to previously unseen data, positioning them as promising tools for optically-assisted neural networks. With this study, in fact, we want 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.