English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/188797
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

Reinforcement learning in a large-scale photonic recurrent neural network

AuthorsBueno Moragues, Julián; Maktoobi, Sheler; Froehly, L.; Fischer, Ingo ; Jacquot, Maxime; Larger, Laurent ; Brunner, Daniel
Issue Date2018
PublisherOptical Society of America
CitationOptica 5(6): 756-760 (2018)
AbstractPhotonic neural network implementation has been gaining considerable attention as a potentially disruptive future technology. Demonstrating learning in large-scale neural networks is essential to establish photonic machine learning substrates as viable information processing systems. Realizing photonic neural networks with numerous nonlinear nodes in a fully parallel and efficient learning hardware has been lacking so far. We demonstrate a network of up to 2025 diffractively coupled photonic nodes, forming a large-scale recurrent neural network. Using a digital micro mirror device, we realize reinforcement learning. Our scheme is fully parallel, and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges, and we achieve very good performance.
Publisher version (URL)https://doi.org/10.1364/OPTICA.5.000756
URIhttp://hdl.handle.net/10261/188797
DOIhttp://dx.doi.org/10.1364/OPTICA.5.000756
E-ISSN2334-2536
Appears in Collections:(IFISC) Artículos
Files in This Item:
File Description SizeFormat 
accesoRestringido.pdf59,24 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.