Reinforcement learning in a large-scale photonic recurrent neural network

J. Bueno, S. Maktoobi, L. Froehly, I. Fischer, M. Jacquot, L. Larger, D. Brunner

Research output: Contribution to journalArticle

77 Citations (Scopus)
6 Downloads (Pure)

Abstract

Photonic 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.

Original languageEnglish
Pages (from-to)756-760
Number of pages5
JournalOptica
Volume5
Issue number6
DOIs
Publication statusPublished - 20 Jun 2018

Keywords

  • neural networks
  • nonlinear optics
  • optical neural systems

Fingerprint Dive into the research topics of 'Reinforcement learning in a large-scale photonic recurrent neural network'. Together they form a unique fingerprint.

Cite this