Greedy Boolean Learning in Photonic Recurrent Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Greedy Boolean Learning in Photonic Recurrent Neural Networks

Abstract

We have recently succeeded in the implementation of a large scale recurrent photonic neural network hosting up to 2025 photonic neurons. All net-work internal and readout connections are physically implemented with fully par-allel technology. Based on a digital micro-mirror array, we can train the Boolean readout weights using a greedy version of reinforcement learning. We find that the learning excellently converges. Furthermore, it appears to possess a conven-iently convex-like cost-function and demonstrates exceptional scalability of the learning effort with system size.
No file

Dates and versions

hal-02383981 , version 1 (28-11-2019)

Identifiers

  • HAL Id : hal-02383981 , version 1

Cite

Louis Andreoli, Javier Porte, Maxime Jacquot, Laurent Larger, Daniel Brunner, et al.. Greedy Boolean Learning in Photonic Recurrent Neural Networks. European Material Research Society annual meeting, Sep 2019, Warsaw, Poland. ⟨hal-02383981⟩
63 View
0 Download

Share

Gmail Facebook X LinkedIn More