Literature DB >> 23388891

Optoelectronic reservoir computing: tackling noise-induced performance degradation.

M C Soriano1, S Ortín, D Brunner, L Larger, C R Mirasso, I Fischer, L Pesquera.   

Abstract

We present improved strategies to perform photonic information processing using an optoelectronic oscillator with delayed feedback. In particular, we study, via numerical simulations and experiments, the influence of a finite signal-to-noise ratio on the computing performance. We illustrate that the performance degradation induced by noise can be compensated for via multi-level pre-processing masks.

Year:  2013        PMID： 23388891     DOI： 10.1364/OE.21.000012

Source DB:  PubMed          Journal:  Opt Express        ISSN： 1094-4087            Impact factor:   3.894


  7 in total

Review 1.  Minimal approach to neuro-inspired information processing.

Authors:  Miguel C Soriano; Daniel Brunner; Miguel Escalona-Morán; Claudio R Mirasso; Ingo Fischer
Journal:  Front Comput Neurosci       Date:  2015-06-02       Impact factor: 2.380

2.  Low-Loss Photonic Reservoir Computing with Multimode Photonic Integrated Circuits.

Authors:  Andrew Katumba; Jelle Heyvaert; Bendix Schneider; Sarah Uvin; Joni Dambre; Peter Bienstman
Journal:  Sci Rep       Date:  2018-02-08       Impact factor: 4.379

3.  Photonic reinforcement learning based on optoelectronic reservoir computing.

Authors:  Kazutaka Kanno; Atsushi Uchida
Journal:  Sci Rep       Date:  2022-03-08       Impact factor: 4.996

4.  Leveraging plant physiological dynamics using physical reservoir computing.

Authors:  Olivier Pieters; Tom De Swaef; Michiel Stock; Francis Wyffels
Journal:  Sci Rep       Date:  2022-07-22       Impact factor: 4.996

5.  Parallel photonic information processing at gigabyte per second data rates using transient states.

Authors:  Daniel Brunner; Miguel C Soriano; Claudio R Mirasso; Ingo Fischer
Journal:  Nat Commun       Date:  2013       Impact factor: 14.919

6.  A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron.

Authors:  S Ortín; M C Soriano; L Pesquera; D Brunner; D San-Martín; I Fischer; C R Mirasso; J M Gutiérrez
Journal:  Sci Rep       Date:  2015-10-08       Impact factor: 4.379

7.  Fully analogue photonic reservoir computer.

Authors:  François Duport; Anteo Smerieri; Akram Akrout; Marc Haelterman; Serge Massar
Journal:  Sci Rep       Date:  2016-03-03       Impact factor: 4.379
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.