Optica Open
Browse
arXiv.svg (5.58 kB)

Reinforcement Learning in a large scale photonic Recurrent Neural Network

Download (5.58 kB)
preprint
posted on 2023-11-30, 17:35 authored by Julian Bueno, Sheler Maktoobi, Luc Froehly, Ingo Fischer, Maxime Jacquot, Laurent Larger, Daniel Brunner
Photonic Neural Network implementations have 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 was lacking so far. We demonstrate a network of up to 2500 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.

History

Disclaimer

This arXiv metadata record was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv.

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC