activity
20082023
most citedReinforcement Learning in a large scale photonic Recurrent Neural Network

407 citations · 1.6k across the 25 of their papers we have counts for

collaborators

27 papers

physics.optics2023★ 6 cited

Deterministic and stochastic coarsening control in optically-addressed spatial light modulators subject to optical feedback

Vladimir V. Semenov, Xavier Porte, Laurent Larger +1

Phase separation accompanied by further domain growth and coarsening is a phenomenon common to a broad variety of dynamical systems. In this connection, controlling such processes…

cs.ET2021★ 163 cited

Tutorial: Photonic Neural Networks in Delay Systems

D. Brunner, B. Penkovsky, B. A. Marquez +3

Photonic delay systems have revolutionized the hardware implementation of Recurrent Neural Networks and Reservoir Computing in particular. The fundamental principles of Reservoir C…

physics.optics2021★ 14 cited

Two-color optically-addressed spatial light modulator as generic spatio-temporal systems

Vladimir Semenov, Xavier Porte, Ibrahim Abdulhalim +2

Nonlinear spatio-temporal systems are the basis for countless physical phenomena in such diverse fields as ecology, optics, electronics and neuroscience. The canonical approach to…

cs.ET2021

Nonlinear photonic dynamical systems for unconventional computing

Daniel Brunner, Laurent Larger, Miguel C. Soriano

Driven by the remarkable breakthroughs during the past decade, photonics neural networks have experienced a revival. Here, we provide a general overview of progress over the past d…

cs.NE2021★ 49 cited

Understanding and mitigating noise in trained deep neural networks

Nadezhda Semenova, Laurent Larger, Daniel Brunner

Deep neural networks unlocked a vast range of new applications by solving tasks of which many were previously deemed as reserved to higher human intelligence. One of the developmen…

cs.NE2020★ 14 cited

Boolean learning under noise-perturbations in hardware neural networks

Louis Andreoli, Xavier Porte, Stéphane Chrétien +3

A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems ha…