Large-Scale Spatiotemporal Photonic Reservoir Computer for Image Classification - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Journal of Selected Topics in Quantum Electronics Année : 2020

Large-Scale Spatiotemporal Photonic Reservoir Computer for Image Classification

Résumé

We propose a scalable photonic architecture for implementation of feedforward and recurrent neural networks to perform the classification of handwritten digits from the MNIST database. Our experiment exploits off-the-shelf optical and electronic components to currently achieve a network size of 16,384 nodes. Both network types are designed within the the reservoir computing paradigm with randomly weighted input and hidden layers. Using various feature extraction techniques (e.g. histograms of oriented gradients, zoning, Gabor filters) and a simple training procedure consisting of linear regression and winner-takes-all decision strategy, we demonstrate numerically and experimentally that a feedforward network allows for classification error rate of 1%, which is at the state-of-the-art for experimental implementations and remains competitive with more advanced algorithmic approaches. We also investigate recurrent networks in numerical simulations by explicitly activating the temporal dynamics, and predict a performance improvement over the feedforward configuration.
Fichier principal
Vignette du fichier
antonik2020large_hal-02403762.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02403762 , version 1 (11-05-2020)

Identifiants

Citer

Piotr Antonik, Nicolas Marsal, Damien Rontani. Large-Scale Spatiotemporal Photonic Reservoir Computer for Image Classification. IEEE Journal of Selected Topics in Quantum Electronics, 2020, 26 (1), pp.1-12. ⟨10.1109/JSTQE.2019.2924138⟩. ⟨hal-02403762⟩
103 Consultations
115 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More