Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Photonic processing for a 56 GBaud PAM-4 100 km Transmission System

  • Estébanez, Irene
  • Li, Shi
  • Schwind, Janek
  • Fischer, Ingo
  • Pachnicke, Stephan
  • Argyris, Apostolos
Trabajo presentado en el IFISC Poster Party (online).-- The IFISC Poster Party is an annual activity where PhD students and postdoctoral researchers of IFISC present their research in a poster format.-- Nonlinear Photonics., This work received funding from MINECO (Spain), through project TEC2016-80063-C3 (AEI/FEDER, UE), from the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (MDM-2017-0711) and from the European Union's Horizon 2020 Research and Innovation Programme under the Marie-Skłodowska Curie grant agreement No 860360., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

An Integrated Photorefractive Analog Matrix-Vector Multiplier for Machine Learning

  • Vlieg, Elger A.
  • Talandier, Lucas
  • Dangel, Roger
  • Horst, Folkert
  • Offrein, Bert J.
AI is fueling explosive growth in compute demand that traditional digital chip architectures cannot keep up with. Analog crossbar arrays enable power efficient synaptic signal processing with linear scaling on neural network size. We present a photonic photorefractive crossbar array for neural network training and inference on local analog memory. We discuss the concept and present results based on the first prototype hardware., This research was funded by European Union’s Horizon 2020 research and innovation program, grant numbers 828841 (ChipAI) and 860360 (Post-Digital)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Nonlinear photonic dynamical systems for unconventional computing

  • Brunner, Daniel
  • Larger, Laurent
  • Soriano, Miguel C.
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 decade, and sketch a roadmap of important future developments. We focus on photonic implementations of the reservoir computing machine learning paradigm, which offers a conceptually simple approach that is amenable to hardware implementations. In particular, we provide an overview of photonic reservoir computing implemented via either spatio temporal or delay dynamical systems. Going beyond reservoir computing, we discuss recent advances and future challenges of photonic implementations of deep neural networks, of the quest for learning methods that are hardware-friendly as well as realizing autonomous photonic neural networks, i.e. with minimal digital electronic auxiliary hardware., We acknowledge the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (MDM-2017-0711) and through the QUARESC project (PID2019-109094GB-C22/AEI/10.13039/501100011033), and through the Region Bourgogne Franche-Comt ́e, the French National Research Agency via EUR EIPHI program (Contract No. ANR-17-EURE-0002), and the Volkswagen Foundation (NeuroQNet II) and the European Union’s Horizon 2020 research and innovation program under the Marie Sk lodowska-Curie Grant Agreements No. 860360 (POST DIGITAL). The work of MCS has been supported by MICINN/AEI/FEDER and the University of the Balearic Islands through a “Ramon y Cajal” Fellowship (RYC-2015-18140)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Nonlinear photonic dynamical systems for unconventional computing

  • Brunner, Daniel
  • Larger, Laurent
  • Soriano, Miguel C.
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 decade, and sketch a roadmap of important future developments. We focus on photonic implementations of the reservoir computing machine learning paradigm, which offers a conceptually simple approach that is amenable to hardware implementations. In particular, we provide an overview of photonic reservoir computing implemented via either spatio temporal or delay dynamical systems. Going beyond reservoir computing, we discuss recent advances and future challenges of photonic implementations of deep neural networks, of the quest for learning methods that are hardware-friendly as well as realizing autonomous photonic neural networks, i.e. with minimal digital electronic auxiliary hardware., We acknowledge the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (MDM-2017-0711) and through the QUARESC project (PID2019-109094GB-C22/AEI/10.13039/501100011033), and through the Region Bourgogne Franche-Comt ́e, the French National Research Agency via EUR EIPHI program (Contract No. ANR-17-EURE-0002), and the Volkswagen Foundation (NeuroQNet II) and the European Union’s Horizon 2020 research and innovation program under the Marie Sk lodowska-Curie Grant Agreements No. 860360 (POST DIGITAL). The work of MCS has been supported by MICINN/AEI/FEDER and the University of the Balearic Islands through a “Ramon y Cajal” Fellowship (RYC-2015-18140)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Photonic neuromorphic technologies in optical communications

  • Argyris, Apostolos
Machine learning (ML) and neuromorphic computing have been enforcing problem-solving in many applications. Such approaches found fertile ground in optical communications, a technological field that is very demanding in terms of computational speed and complexity. The latest breakthroughs are strongly supported by advanced signal processing, implemented in the digital domain. Algorithms of different levels of complexity aim at improving data recovery, expanding the reach of transmission, validating the integrity of the optical network operation, and monitoring data transfer faults. Lately, the concept of reservoir computing (RC) inspired hardware implementations in photonics that may offer revolutionary solutions in this field. In a brief introduction, I discuss some of the established digital signal processing (DSP) techniques and some new approaches based on ML and neural network (NN) architectures. In the main part, I review the latest neuromorphic computing proposals that specifically apply to photonic hardware and give new perspectives on addressing signal processing in optical communications. I discuss the fundamental topologies in photonic feed-forward and recurrent network implementations. Finally, I review the photonic topologies that were initially tested for channel equalization benchmark tasks, and then in fiber transmission systems, for optical header recognition, data recovery, and modulation format identification., The author would like to acknowledge the support of the Severo Ochoa and Maria de Maeztu Program for Centers and Units of Excellence in R&D, grant MDM-2017-0711 (funded by MCIN/AEI/10.13039/501100011033), the European Union’s Horizon 2020 Future and Emerging Technologies program (Grant Agreement No. 899265, ADOPD), the European Union’s Horizon 2020 Marie-Skłodowska Curie Training Network program (Grand agreement No. 860360, POST-DIGITAL) and the Ministerio de Ciencia e Innovación through the project DECAPH (funded by PID2019-111537GB-C21/AEI/10.13039/501100011033).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatio-temporal systems using scalable neural networks

  • Goldmann, Mirko
  • Mirasso, Claudio R.
  • Fischer, Ingo
  • Soriano, Miguel C.
We design scalable neural networks adapted to translational symmetries in dynamical systems, capable of inferring untrained high-dimensional dynamics for different system sizes. We train these networks to predict the dynamics of delay-dynamical and spatio-temporal systems for a single size. Then, we drive the networks by their own predictions. We demonstrate that by scaling the size of the trained network, we can predict the complex dynamics for larger or smaller system sizes. Thus, the network learns from a single example and, by exploiting symmetry properties, infers entire bifurcation diagrams., We acknowledge support of the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (Grant No. MDM-2017-0711 funded by Grant No. MCIN/AEI/10.13039/501100011033) and through the QUARESC Project (Projects No. PID2019-109094GB-C21 and No. -C22/AEI/10.13039/501100011033) and the DECAPH Project (Projects No. PID2019-111537GB-C21 and No. -C22/AEI/10.13039/501100011033). M.G. acknowledges financial support by the European Union's H2020 Excellent Science Program under the Marie Skłodowska-Curie Grant Agreement No. 860360 (POST DIGITAL). This work has been partially funded by the European Union's H2020 Excellent Science Future and Emerging Technologies program under Grant Agreement No. 899265 (ADOPD)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatiotemporal systems using scalable neural networks

  • Goldmann, Mirko
  • Mirasso, Claudio R.
  • Fischer, Ingo
  • Soriano, Miguel C.
We design scalable neural networks adapted to translational symmetries in dynamical systems, capable of inferring untrained high-dimensional dynamics for different system sizes. We train these networks to predict the dynamics of delay-dynamical and spatiotemporal systems for a single size. Then, we drive the networks by their own predictions. We demonstrate that by scaling the size of the trained network, we can predict the complex dynamics for larger or smaller system sizes. Thus, the network learns from a single example and by exploiting symmetry properties infers entire bifurcation diagrams., We acknowledge support of the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (Grant No. MDM-2017-0711 funded by Grant No. MCIN/AEI/10.13039/501100011033) and through the QUARESC Project (Projects No. PID2019-109094GB-C21 and No. -C22/AEI/10.13039/501100011033) and the DECAPH Project (Projects No. PID2019-111537GB-C21 and No. -C22/AEI/10.13039/501100011033). M.G. acknowledges financial support by the European Union's H2020 Excellent Science Program under the Marie Skłodowska-Curie Grant Agreement No. 860360 (POST DIGITAL). This work has been partially funded by the European Union's H2020 Excellent Science Future and Emerging Technologies program under Grant Agreement No. 899265 (ADOPD)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Exploiting oscillatory dynamics of delay systems for reservoir computing

  • Goldmann, Mirko
  • Fischer, Ingo
  • Mirasso, Claudio R.
  • Soriano, Miguel C.
Nonlinear dynamical systems exhibiting inherent memory can process temporal information by exploiting their responses to input drives. Reservoir computing is a prominent approach to leverage this ability for time-series forecasting. The computational capabilities of analog computing systems often depend on both the dynamical regime of the system and the input drive. Most studies have focused on systems exhibiting a stable fixed-point solution in the absence of input. Here, we go beyond that limitation, investigating the computational capabilities of a paradigmatic delay system in three different dynamical regimes. The system we chose has an Ikeda-type nonlinearity and exhibits fixed point, bistable, and limit-cycle dynamics in the absence of input. When driving the system, new input-driven dynamics emerge from the autonomous ones featuring characteristic properties. Here, we show that it is feasible to attain consistent responses across all three regimes, which is an essential prerequisite for the successful execution of the tasks. Furthermore, we demonstrate that we can exploit all three regimes in two time-series forecasting tasks, showcasing the versatility of this paradigmatic delay system in an analog computing context. In all tasks, the lowest prediction errors were obtained in the regime that exhibits limit-cycle dynamics in the undriven reservoir. To gain further insights, we analyzed the diverse time-distributed node responses generated in the three regimes of the undriven system. An increase in the effective dimensionality of the reservoir response is shown to affect the prediction error, as also fine-tuning of the distribution of nonlinear responses. Finally, we demonstrate that a trade-off between prediction accuracy and computational speed is possible in our continuous delay systems. Our results not only provide valuable insights into the computational capabilities of complex dynamical systems but also open a new perspective on enhancing the potential of analog computing systems implemented on various hardware platforms., This work was supported by the Spanish State Research Agency through the QUARESC project (Nos. PID2019-109094GB-C21 and PID2019-109094GB-C22/AEI/10.13039/501100011033). M.G. acknowledges financial support by the European Union’s Horizon 2020 program under the Marie Skłodowska-Curie Grant Agreement No. 860360 (POST DIGITAL). This work was partially funded by the European Union’s Horizon 2020 framework program under Grant Agreement No. 899265 (ADOPD) and the Program for Units of Excellence in R&D María de Maeztu (CEX2021-001164-M /10.13039/501100011033)., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Adaptive control of recurrent neural networks using conceptors

  • Pourcel, Guillaume
  • Goldmann, Mirko
  • Fischer, Ingo
  • Soriano, Miguel C.
Recurrent neural networks excel at predicting and generating complex high-dimensional temporal patterns. Due to their inherent nonlinear dynamics and memory, they can learn unbounded temporal dependencies from data. In a machine learning setting, the network's parameters are adapted during a training phase to match the requirements of a given task/problem increasing its computational capabilities. After the training, the network parameters are kept fixed to exploit the learned computations. The static parameters, therefore, render the network unadaptive to changing conditions, such as an external or internal perturbation. In this paper, we demonstrate how keeping parts of the network adaptive even after the training enhances its functionality and robustness. Here, we utilize the conceptor framework and conceptualize an adaptive control loop analyzing the network's behavior continuously and adjusting its time-varying internal representation to follow a desired target. We demonstrate how the added adaptivity of the network supports the computational functionality in three distinct tasks: interpolation of temporal patterns, stabilization against partial network degradation, and robustness against input distortion. Our results highlight the potential of adaptive networks in machine learning beyond training, enabling them to not only learn complex patterns but also dynamically adjust to changing environments, ultimately broadening their applicability., The authors acknowledge the support of the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (No. CEX2021-001164-M), the INFOLANET projects (No. PID2022-139409NB-I00) funded by the MCIN/AEI/10.13039/501100011033, and through the QUARESC project (Nos. PID2019-109094GB-C21 and -C22/AEI/10.13039/501100011033) and the DECAPH project (Nos. PID2019-111537GB-C21 and -C22/AEI/10.13039/501100011033). All authors acknowledge financial support by the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie Grant Agreement No. 860360 (POST DIGITAL)., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Adaptive control of recurrent neural networks using conceptors

  • Pourcel, Guillaume
  • Goldmann, Mirko
  • Fischer, Ingo
  • Soriano, Miguel C.
Recurrent Neural Networks excel at predicting and generating complex high-dimensional temporal patterns. Due to their inherent nonlinear dynamics and memory, they can learn unbounded temporal dependencies from data. In a Machine Learning setting, the network's parameters are adapted during a training phase to match the requirements of a given task/problem increasing its computational capabilities. After the training, the network parameters are kept fixed to exploit the learned computations. The static parameters thereby render the network unadaptive to changing conditions, such as external or internal perturbation. In this manuscript, we demonstrate how keeping parts of the network adaptive even after the training enhances its functionality and robustness. Here, we utilize the conceptor framework and conceptualize an adaptive control loop analyzing the network's behavior continuously and adjusting its time-varying internal representation to follow a desired target. We demonstrate how the added adaptivity of the network supports the computational functionality in three distinct tasks: interpolation of temporal patterns, stabilization against partial network degradation, and robustness against input distortion. Our results highlight the potential of adaptive networks in machine learning beyond training, enabling them to not only learn complex patterns but also dynamically adjust to changing environments, ultimately broadening their applicability., The authors acknowledge the support of the Spanish State Research Agency, through the Severo Ochoa 10 and María de Maeztu Program for Centers and Units of Excellence in R&D (CEX2021-001164-M), the IN- FOLANET projects (PID2022-139409NB-I00) funded by the MCIN/AEI/10.13039/501100011033 and through the QUARESC project (PID2019-109094GB-C21 and -C22/ AEI / 10.13039/501100011033) and the DE- CAPH project (PID2019-111537GB-C21 and -C22/ AEI / 10.13039/501100011033). All authors acknowledge financial support by the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No. 860360 (POST DIGITAL)., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A photonics perspective on computing with physical substrates

  • Abreu, S.
  • Boikov, I.
  • Goldmann, M.
  • Jonuzi, T.
  • Lupo, A.
  • Masaad, S.
  • Nguyen, L.
  • Picco, E.
  • Pourcel, G.
  • Skalli, A.
  • Talandier, L.
  • Vettelschoss, B.
  • Vlieg, E. A.
  • Argyris, Apostolos
  • Bienstman, P.
  • Brunner, Daniel
  • Dambre, Joni
  • Daudet, L.
  • Domenéch, J. D.
  • Fischer, Ingo
  • Horst, Folkert
  • Massar, Serge
  • Mirasso, Claudio R.
  • Offrein, B. J.
  • Rossi, A.
  • Soriano, Miguel C.
  • Sygletos, S.
  • Turitsyn, S. K.
We provide a perspective on the fundamental relationship between physics and computation, exploring the conditions under which a physical system can be harnessed for computation and the practical means to achieve this. Unlike traditional digital computers that impose discreteness on continuous substrates, unconventional computing embraces the inherent properties of physical systems. Exploring simultaneously the intricacies of physical implementations and applied computational paradigms, we discuss the interdisciplinary developments of unconventional computing. Here, we focus on the potential of photonic substrates for unconventional computing, implementing artificial neural networks to solve data-driven machine learning tasks. Several photonic neural network implementations are discussed, highlighting their potential advantages over electronic counterparts in terms of speed and energy efficiency. Finally, we address the challenges of achieving learning and programmability within physical substrates, outlining key strategies for future research., We acknowledge financial support by the European Union’s Horizon 2020 program under the Marie Skłodowska-Curie grant agreement No. 860360 (POST DIGITAL), by the Fonds de la Recherche Scientifique - FNRS, Belgium under funding EOS n°40007536 and CDR n°40021243, and by the Spanish State Research Agency, through the INFOLANET and María de Maeztu projects (PID2022-139409NB-I00 and CEX2021-001164-M) funded by the MCIN/AEI/10.13039/501100011033 ., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Speedup of an all-optical delay-based reservoir computer via input rate increase and bandwidth enhancement

  • Goldmann, Mirko
  • Estébanez, Irene
  • Mirasso, Claudio R.
  • Fischer, Ingo
  • Argyris, Apostolos
  • Soriano, Miguel C.
We demonstrate the acceleration of an all-optical delay-based reservoir computer (RC) for time-series prediction. The RC system comprises a semiconductor laser with delayed optical feedback, driven by an injection laser modulated with a time-multiplexed input signal. We numerically and experimentally investigate how node separation, the emission frequency of the lasers, and feedback strength influence prediction performance, with a particular focus on the Mackey-Glass chaotic time series. Numerical simulations, based on the Lang-Kobayashi rate equations, reveal that a small node separation of 12 ps yields superior performance by exploiting bandwidth enhancement. Critically, we find that reducing an input period well below the delay time, and optimizing the number of virtual nodes, significantly increases the inference rate to 0.417 GSa/s, a 10-fold improvement over processing at the rate of the delay time. In experimental realizations, we can confirm these findings, showing good agreement with numerical predictions. This speedup also enhances energy efficiency, reducing the energy per inference from 26.5 to 2.6 nJ in our proof-of-concept settings. The results highlight the importance of tuning time scales inherent to both the physical substrate and the computational task for optimized, high-speed, and energy-efficient reservoir computing., The authors acknowledge scientific discussions with Elger Vlieg, Lucas Talandier, and Tigers Jonuzi, and acknowledge the support of the Spanish State Research Agency, through the Severo Ochoa and María de Maeztu Program for Centers and Units of Excellence in R&D (No. CEX2021-001164-M) and the INFOLANET project (No. PID2022-139409NB-I00) funded by No. MCIN/AEI/10.13039/501100011033. All authors acknowledge the financial support by the European Union Research and Innovation Program under the Marie Skłodowska–Curie Grant Agreement Nos. 860360 (POST DIGITAL) and 101169118 (POST DIGITAL+)., With funding from the Spanish government through the "María de Maeztu Unit of Excellence" accreditation (CEX2021-001164-M), Peer reviewed