Reinforcement learning in a large-scale photonic recurrent neural network

Show simple item record Bueno, J. Maktoobi, S. Froehly, L. Fischer, I. Jacquot, M. Larger, L. Brunner, D. 2019-12-13T08:08:34Z
dc.description.abstract [eng] 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.
dc.format application/pdf
dc.relation.ispartof Optica, 2018, vol. 5, num. 6, p. 756-760
dc.rights , 2018
dc.subject.classification 535 - Òptica
dc.subject.other 535 - Optics
dc.title Reinforcement learning in a large-scale photonic recurrent neural network
dc.type info:eu-repo/semantics/article 2019-12-13T08:08:34Z info:eu-repo/date/embargoEnd/2026-12-31
dc.embargo 2026-12-31
dc.subject.keywords Nonlinear Photonics
dc.subject.keywords photonics
dc.subject.keywords nonlinear dynamics
dc.subject.keywords Information processing
dc.subject.keywords reservoir computing
dc.rights.accessRights info:eu-repo/semantics/embargoedAccess

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Repository

Advanced Search


My Account