Reinforcement Learning in a large scale photonic Recurrent Neural Network
By Julián Bueno, S. Maktoobi, L. Froehly, Ingo Fischer, Maxime Jacquot, Laurent Larger, Daniel Brunner. Optica, 2017
322 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/9fba31ec64ce23405e36cabf4f31c2fe2d12826c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Electrical and Electronic Engineering
Citations in the corpus
- Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale (2018, background): “RNNs that can learn from sequential inputs have been realized on a photonic platform very recently but not yet in nanophotonics [181, 182].”
- All-optical neural network with nonlinear activation functions (2019, background): “Recently ONNs basing on nanophotonic circuits [32] and light-wave linear diffraction and interference [33] have been demonstrated for efficient machine learning, but the nonlinear optical activation functions are still in absence for deep networks [31, 34].”