Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Kostas Sozos"'
Autor:
Aris Tsirigotis, George Sarantoglou, Menelaos Skontranis, Stavros Deligiannidis, Kostas Sozos, Giannis Tsilikas, Dimitris Dermanis, Adonis Bogris, Charis Mesaritakis
Publikováno v:
Intelligent Computing, Vol 2 (2023)
We provide an overview of the rapidly evolving landscape of integrated photonic neuromorphic architectures, specifically targeting the implementation of convolutional neural networks. The exploding research momentum stems from the well-known advantag
Externí odkaz:
https://doaj.org/article/e3ae1f29fd5649429f2b011e5f92bb70
Autor:
Menelaos Skontranis, George Sarantoglou, Kostas Sozos, Thomas Kamalakis, Charis Mesaritakis, Adonis Bogris
Publikováno v:
Neuromorphic Computing and Engineering, Vol 3, Iss 4, p 044003 (2023)
In this work, we introduce Fabry–Perot lasers as neuromoprhic nodes in the context of time-delayed reservoir computing and extreme learning machine (ELM) for the processing of temporal signals and the high-speed classification of images. By exploit
Externí odkaz:
https://doaj.org/article/7d0f335afc5945db92e5ea192ffc231f
Publikováno v:
Journal of Lightwave Technology. :1-9
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80824b9db63de74183f48e0ec58b855a
https://doi.org/10.1109/jlt.2023.3235278
https://doi.org/10.1109/jlt.2023.3235278
Publikováno v:
IEEE Journal of Quantum Electronics. 57:1-7
In this paper we propose and numerically study a neuromorphic computing scheme that applies delay-based reservoir computing in a laser system consisting of two mutually coupled phase modulated lasers. The scheme can be monolithic integrated in a stra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40134398f79009ae2e3e8e0e724c3cab
https://doi.org/10.1109/jqe.2021.3104855
https://doi.org/10.1109/jqe.2021.3104855
Publikováno v:
AI and Optical Data Sciences III.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82475995268f50b27051b9d633858b1e
https://doi.org/10.1117/12.2607438
https://doi.org/10.1117/12.2607438
Autor:
Kostas Sozos, Adonis Bogris, Peter Bienstman, George Sarantoglou, Stavros Deligiannidis, Charis Mesaritakis
Publikováno v:
COMMUNICATIONS ENGINEERING
Neuromorphic Computing implemented in photonic hardware is one of the most promising routes towards achieving machine learning processing at the picosecond scale, with minimum power consumption. In this work, we present a new concept for realizing ph
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22de3d7e4e1f406d3eafb32be83b66e0
Publikováno v:
Optical Fiber Communication Conference (OFC) 2022.
We present experimental results regarding dispersion equalization in IM-DD transmission systems with an extreme learning machine based on a Fabry Perot laser. The exploitation of two longitudinal modes yields enhanced computational power and processi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::234c45f2fe4526270ded90f07c0e0053
https://doi.org/10.1364/ofc.2022.m1g.3
https://doi.org/10.1364/ofc.2022.m1g.3
Publikováno v:
OFC
We propose a reservoir computing system consisting of two mutually coupled phase modulated lasers. The scheme can be monolithic integrated and extends the reach of 25Gbaud PAM-4 signals up to 55 km in the C-band.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::785550dba671038e42873734ec4a2726
https://doi.org/10.1364/ofc.2021.w6a.4
https://doi.org/10.1364/ofc.2021.w6a.4
Publikováno v:
Photonics in Switching and Computing 2021.
In this paper we propose a new neuromorphic photonic integrated architecture based on recurrent optical filters as core reservoir computing building blocks forming an efficient hardware accelerator for pattern recognition in telecom and imaging appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e9807b2a5152086885fa46477a97eae2
https://doi.org/10.1364/psc.2021.w1c.2
https://doi.org/10.1364/psc.2021.w1c.2