55 citations · 72 across the 11 of their papers we have counts for
11 papers
Recurrent Optical Spectrum Slicers as multi-λ processors for WDM optical equalization of IM/DD channels
Kostas Sozos, Francesco Da Ros, George Sarantoglou +2
We report recurrent optical spectrum slicers as multi-wavelength optical processors in dispersion impaired IM/DD transmission systems with the use of programmable photonics. We dem…
Integrated recurrent optical spectral slicer for equalization of 100-km C-band IM/DD transmission
I. Teofilovic, K. Sozos, H. Liu +10
A silicon-photonics recurrent spectral filter is designed, fabricated, and system tested to pro-vide optical pre-processing in a 32-GBd PAM-4 C-band transmission. Performance below…
Reconfigurable Integrated Photonic Chips as Dual-Purpose Neuromorphic Accelerators and Physical Unclonable Functions
George Sarantoglou, Francesco Da Ros, Kostas Sozos +2
In this work, we experimentally validate the dual use of a reconfigurable photonic integrated mesh as a neuromorphic accelerator, targeting signal equalization, and as a physical u…
Experimental Analysis of a Self-Coherent M-QAM Receiver by Means of Recurrent Optical Spectrum Slicing and Direct Detection
Kostas Sozos, Francesco Da Ros, Senior Member Optica +6
High order modulation formats constitute the most prominent way for increasing spectral efficiency in transmission systems. Coherent transceivers that support such higher order for…
Experimental Investigation of a Recurrent Optical Spectrum Slicing Receiver for Intensity Modulation/Direct Detection systems using Programmable Photonics
Kostas Sozos, Francesco Da Ros, Metodi P. Yankov +4
In this paper, we experimentally validate our previous numerical works in recurrent optical spectrum slicing (ROSS) accelerators for dispersion compensation in high-speed IM/DD lin…
Unconventional Computing based on Four Wave Mixing in Highly Nonlinear Waveguides
Kostas Sozos, Stavros Deligiannidis, Charis Mesaritakis +1
In this work we numerically analyze a photonic unconventional accelerator based on the four-wave mixing effect in highly nonlinear waveguides. The proposed scheme can act as a full…
Multichannel Nonlinear Equalization in Coherent WDM Systems based on Bi-directional Recurrent Neural Networks
Stavros Deligiannidis, Kyle R. H. Bottrill, Kostas Sozos +3
Kerr nonlinearity in the form of self- and cross-phase modulation imposes a fundamental limitation to the capacity of wavelength division multiplexed (WDM) optical communication sy…
Integrated Photonic Accelerator Based on Optical Spectrum Slicing for Convolutional Neural Networks
Aris Tsirigotis, George Sarantoglou, Stavros Deligiannidis +3
In this work we numerically analyze a passive photonic integrated neuromorphic accelerator based on hardware-friendly optical spectrum slicing nodes. The proposed scheme can act as…
High Speed Photonic Neuromorphic Computing Using Recurrent Optical Spectrum Slicing Neural Networks
K. Sozos, A. Bogris, P. Bienstman +3
Neuromorphic Computing implemented in photonic hardware is one of the most promising routes towards achieving machine learning processing at the picosecond scale, with minimum powe…
Reservoir Computing based on Mutually Injected Phase Modulated Semiconductor Lasers as a monolithic integrated hardware accelerator
Kostas Sozos, Charis Mesaritakis, Adonis Bogris
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 pha…
Spatial Photonic Reservoir Computing based on Non-Linear Phase-to-Amplitude Conversion in Micro-Ring Resonators
Charis Mesaritakis, Kostas Sozos, Dimitris Dermanis +1
We present a photonic reservoir computing, relying on a non-linear phase-to-amplitude mapping process, able to classify in real-time multi-Gbaud time traces subject to transmission…