Low-power multi-mode fiber projector overcomes shallow neural networks classifiers
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 53 references that are in the map. First posted on arXiv 10 Oct 2022.
Builds on
20 of 53 references.
References · 20
- 2018On Lazy Training in Differentiable Programmingcited by 671
- 2019Fantastic Generalization Measures and Where to Find Themcited by 507
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 357
- 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 175
- 2020Generalisation error in learning with random features and the hidden manifold modelcited by 126
- 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 125
- 2020The Gaussian equivalence of generative models for learning with shallow neural networkscited by 113
- 2020Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unitcited by 64
- 2016Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemescited by 40
- 2015Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapsescited by 39
- 2020An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognitioncited by 30
- 2019Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networkscited by 27
8 more
- 2020Entropic gradient descent algorithms and wide flat minimacited by 25
- 2021Learning through atypical "phase transitions" in overparameterized neural networkscited by 21
- 2020Scalable Optical Learning Operatorcited by 19
- 2015Random Projections through multiple optical scattering: Approximating kernels at the speed of lightcited by 16
- 2022Hybrid training of optical neural networkscited by 15
- 2020A complete, parallel and autonomous photonic neural network in a semiconductor multimode lasercited by 6
- 2019Classification of time-domain waveforms using a speckle-based optical reservoir computercited by 3
- 2019Transmission Matrix Inference via Pseudolikelihood Decimationcited by 1
Built on by
Not cited yet.