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

• URL: http://arxiv.org/abs/2210.04745v3
• Date: Wed, 02 Apr 2025 16:17:19 GMT
• Title: Low-power multi-mode fiber projector overcomes shallow neural networks classifiers
• Authors: Daniele Ancora, Matteo Negri, Antonio Gianfrate, Dimitris Trypogeorgos, Lorenzo Dominici, Daniele Sanvitto, Federico Ricci-Tersenghi, Luca Leuzzi,
• Abstract summary: Multi-mode optical fibers stand out as cost-effective and easy-to-handle tools.<n>We cast these fibers into random hardware projectors, transforming an input dataset into a higher dimensional speckled image set.<n>We found that the classification accuracy achieved is higher than that obtained with the standard transmission matrix model.
• Score: 10.161703420607552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Training Hybrid Neural Networks with Multimode Optical Nonlinearities Using Digital Twins [2.8479179029634984]
  We introduce ultrashort pulse propagation in multimode fibers, which perform large-scale nonlinear transformations. Training the hybrid architecture is achieved through a neural model that differentiably approximates the optical system. Our experimental results achieve state-of-the-art image classification accuracies and simulation fidelity.
  arXiv  Detail & Related papers  (2025-01-14T10:35:18Z)
• Optical training of large-scale Transformers and deep neural networks with direct feedback alignment [48.90869997343841]
  We experimentally implement a versatile and scalable training algorithm, called direct feedback alignment, on a hybrid electronic-photonic platform. An optical processing unit performs large-scale random matrix multiplications, which is the central operation of this algorithm, at speeds up to 1500 TeraOps. We study the compute scaling of our hybrid optical approach, and demonstrate a potential advantage for ultra-deep and wide neural networks.
  arXiv  Detail & Related papers  (2024-09-01T12:48:47Z)
• Genetically programmable optical random neural networks [0.0]
  We demonstrate a genetically programmable yet simple optical neural network to achieve high performances with optical random projection. Our novel technique finds an optimum kernel and improves initial test accuracies by 8-41% for various machine learning tasks.
  arXiv  Detail & Related papers  (2024-03-19T06:55:59Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Deep Learning with Passive Optical Nonlinear Mapping [9.177212626554505]
  We introduce a design that leverages multiple scattering in a reverberating cavity to passively induce optical nonlinear random mapping. We show we can perform optical data compression, facilitated by multiple scattering in the cavity, to efficiently compress and retain vital information. Our findings pave the way for novel algorithms and architectural designs for optical computing.
  arXiv  Detail & Related papers  (2023-07-17T15:15:47Z)
• Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
  We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
  arXiv  Detail & Related papers  (2023-03-17T18:00:27Z)
• An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design [55.62660894625669]
  Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks. We propose a litho-aware data augmentation framework to resolve the dilemma of limited data and improve the machine learning model performance.
  arXiv  Detail & Related papers  (2022-10-27T20:53:39Z)
• Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks [0.7627023515997987]
  We design mass-manufacturable silicon photonic neural networks that cascade our custom designed "photonic mesh" accelerator. We demonstrate in situ backpropagation for the first time to solve classification tasks. Our findings suggest a new training paradigm for photonics-accelerated artificial intelligence based entirely on a physical analog of the popular backpropagation technique.
  arXiv  Detail & Related papers  (2022-05-17T17:13:50Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Learning optical flow from still images [53.295332513139925]
  We introduce a framework to generate accurate ground-truth optical flow annotations quickly and in large amounts from any readily available single real picture. We virtually move the camera in the reconstructed environment with known motion vectors and rotation angles. When trained with our data, state-of-the-art optical flow networks achieve superior generalization to unseen real data.
  arXiv  Detail & Related papers  (2021-04-08T17:59:58Z)
• Neural BRDF Representation and Importance Sampling [79.84316447473873]
  We present a compact neural network-based representation of reflectance BRDF data. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets.
  arXiv  Detail & Related papers  (2021-02-11T12:00:24Z)
• Scalable Optical Learning Operator [0.2399911126932526]
  The presented framework overcomes the energy scaling problem of existing systems without classifying speed. We numerically and experimentally showed the ability of the method to execute several different tasks with accuracy comparable to a digital implementation. Our results indicate that a powerful supercomputer would be required to duplicate the performance of the multimode fiber-based computer.
  arXiv  Detail & Related papers  (2020-12-22T23:06:59Z)
• Scale-, shift- and rotation-invariant diffractive optical networks [0.0]
  Diffractive Deep Neural Networks (D2NNs) harness light-matter interaction over a series of trainable surfaces to compute a desired statistical inference task. Here, we demonstrate a new training strategy for diffractive networks that introduces input object translation, rotation and/or scaling during the training phase. This training strategy successfully guides the evolution of the diffractive optical network design towards a solution that is scale-, shift- and rotation-invariant.
  arXiv  Detail & Related papers  (2020-10-24T02:18:39Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Ensemble learning of diffractive optical networks [0.0]
  We numerically demonstrated that ensembles of N=14 and N=30 D2NNs achieve blind testing accuracies of 61.14% and 62.13%, respectively, on the classification of CIFAR-10 test images. These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset.
  arXiv  Detail & Related papers  (2020-09-15T05:02:50Z)
• Large-scale spatiotemporal photonic reservoir computer for image classification [0.8701566919381222]
  We propose a scalable photonic architecture for implementation of feedforward and recurrent neural networks to perform the classification of handwritten digits. Our experiment exploits off-the-shelf optical and electronic components to currently achieve a network size of 16,384 nodes.
  arXiv  Detail & Related papers  (2020-04-06T10:22:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.