Reinforcement Learning in a Large Scale Photonic Network - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Reinforcement Learning in a Large Scale Photonic Network

Résumé

We experimentally create a neural network, implementing 2025 connections in parallel. We numerically validate the scheme for at least 34000 photonic neurons. We demonstrate photonic efficiently converging reinforcement learning, prediction a chaotic signal with.
Fichier non déposé

Dates et versions

hal-02300668 , version 1 (29-09-2019)

Identifiants

  • HAL Id : hal-02300668 , version 1

Citer

Sheler Maktoobi, Louis Andreoli, Laurent Larger, Maxime Jacquot, Daniel Brunner. Reinforcement Learning in a Large Scale Photonic Network. Conference on Lasers and Electro-Optics, May 2018, San Jose, United States. ⟨hal-02300668⟩
15 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More