Maxime Jacquot

Maxime Jacquot, FEMTO-ST, Besançon

Photonic Neural Networks

Photonic systems have revolutionized the hardware implementation of Recurrent Neural Networks and Reservoir Computing, in particular. The fundamental principles of Reservoir
Computing strongly facilitate a realization in such complex analog systems. Especially delay systems which potentially provide large numbers of degrees of freedom even in simple architectures, can efficiently be exploited for information processing. The numerous demonstrations of their performance led to a revival of photonic Artificial Neural Network. We also demonstrate learning in large scale neural networks with numerous nonlinear nodes in a fully parallel architecture using SLM. We build a network of up to 2500 diffractively coupled photonic nodes, forming a large scale Recurrent Neural Network. This last scheme is fully parallel and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges and we achieve very good performance.