Results 11 to 20 of about 763 (210)

Photonic reinforcement learning based on optoelectronic reservoir computing [PDF]

Scientific Reports, 2022
Reinforcement learning has been intensively investigated and developed in artificial intelligence in the absence of training data, such as autonomous driving vehicles, robot control, internet advertising, and elastic optical networks.
Kazutaka Kanno, Atsushi Uchida
doaj   +5 more sources

Photonic reservoir computing: a thematic review

JPhys Photonics
Reservoir computing offers a versatile approach to temporal information processing by exploiting the dynamics of nonlinear systems to enable learning with a linear readout.
Mohab Abdalla, Guy Van der Sande, Apostolos Argyris, Fabio Pavanello, Miguel C Soriano, Damien Rontani   +5 more
doaj   +6 more sources

Photonic reservoir computing for nonlinear equalization of 64‐QAM signals with a Kramers–Kronig receiver [PDF]

Nanophotonics, 2023
Peter Bienstman, Joni Dambré
exaly   +2 more sources

Design and Research of Photonic Reservoir Computing for Optical Channel Equalization

Photonics
In this paper, photonic reservoir computing chip architectures for noise equalization in optical fiber communication channels are proposed. These architectures leverage optical computing instead of electrical computing to reduce computational pressure at
Xiaoyan Zuo, Li Pei, Bing Bai, Bowen Bai, Jianshuai Wang, Quan Li, Run Yang   +6 more
doaj   +3 more sources

Time-domain image processing using photonic reservoir computing [PDF]

EPJ Web of Conferences, 2023
Photonic computing has attracted much attention due to its great potential to accelerate artificial neural network operations. However, the processing of a large amount of data, such as image data, basically requires large-scale photonic circuits and is ...
Sunada Satoshi, Yamaguchi Tomoya
doaj   +1 more source

Low-Loss Photonic Reservoir Computing with Multimode Photonic Integrated Circuits. [PDF]

Sci Rep, 2018
AbstractWe present a numerical study of a passive integrated photonics reservoir computing platform based on multimodal Y-junctions. We propose a novel design of this junction where the level of adiabaticity is carefully tailored to capture the radiation loss in higher-order modes, while at the same time providing additional mode mixing that increases ...
Katumba A, Heyvaert J, Schneider B, Uvin S, Dambre J, Bienstman P.   +5 more
europepmc   +5 more sources

Quantum reservoir computing for photonic entanglement witnessing. [PDF]

Sci Adv
Accurately estimating properties of quantum states, such as entanglement, while essential for the development of quantum technologies, remains a challenging task. Standard approaches to property estimation rely on detailed modeling of the measurement apparatus and a priori assumptions on their working principles.
Zia D, Innocenti L, Minati G, Lorenzo S, Suprano A, Di Bartolo R, Spagnolo N, Giordani T, Cimini V, Palma GM, Ferraro A, Sciarrino F, Paternostro M.   +12 more
europepmc   +8 more sources

Scalable wavelength-multiplexing photonic reservoir computing

APL Machine Learning, 2023
Photonic reservoir computing (PRC) is a special hardware recurrent neural network, which is featured with fast training speed and low training cost. This work shows a wavelength-multiplexing PRC architecture, taking advantage of the numerous longitudinal
Rui-Qian Li, Yi-Wei Shen, Bao-De Lin, Jingyi Yu, Xuming He, Cheng Wang   +5 more
doaj   +1 more source

Photonic reservoir computing approaches to nanoscale computation [PDF]

Proceedings of the Second Annual International Conference on Nanoscale Computing and Communication, 2015
This material is based on work in progress. Reservoir computing, originally a training technique for recurrent neural networks, exploits the computation that naturally occurs in physical dynamical systems. Reservoir computing with integrated nanophotonics potentially offers low-power, high-bandwidth signal processing for telecommunication applications.
Andrew Katumba, Peter Bienstman, Joni Dambre   +2 more
openaire   +2 more sources

Connecting reservoir computing with statistical forecasting and deep neural networks

Nature Communications, 2022
Standfirst Among the existing machine learning frameworks, reservoir computing demonstrates fast and low-cost training, and its suitability for implementation in various physical systems.
Lina Jaurigue, Kathy Lüdge
doaj   +1 more source