Pasar al contenido principal

PROCESAMIENTO DE INFORMACION CON REDES DE LASERES ACOPLADOS

PID2022-139409NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE LAS ISLAS BALEARES

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Dynamical stability and chaos in artificial neural network trajectories along training

  • Danovski, Kaloyan
  • Soriano, Miguel C.
  • Lacasa, Lucas
29 pages, 18 figures, The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally interpreted as a trajectory in network space -- a time series of networks -- and thus the training algorithm (e.g. gradient descent optimization of a suitable loss function) can be interpreted as a dynamical system in graph space. In order to illustrate this interpretation, here we study the dynamical properties of this process by analyzing through this lens the network trajectories of a shallow neural network, and its evolution through learning a simple classification task. We systematically consider different ranges of the learning rate and explore both the dynamical and orbital stability of the resulting network trajectories, finding hints of regular and chaotic behavior depending on the learning rate regime. Our findings are put in contrast to common wisdom on convergence properties of neural networks and dynamical systems theory. This work also contributes to the cross-fertilization of ideas between dynamical systems theory, network theory and machine learning., We acknowledge funding from the Spanish Research Agency MCIN/AEI/10.13039/501100011033 via projects DYNDEEP (EUR2021-122007), MISLAND (PID2020-114324GB-C22), INFOLANET (PID2022-139409NB-I00) and the María de Maeztu project CEX2021-001164-M., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación 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
Publicación Otros (Other)

Role of coherence in many-body Quantum Reservoir Computing

  • Palacios, Ana
  • Martínez-Peña, Rodrigo
  • Soriano, Miguel C.
  • Giorgi, Gian Luca
  • Zambrini, Roberta
Quantum Reservoir Computing (QRC) offers potential advantages over classical reservoir computing, including inherent processing of quantum inputs and a vast Hilbert space for state exploration. Yet, the relation between the performance of reservoirs based on complex and many-body quantum systems and non-classical state features is not established. Through an extensive analysis of QRC based on a transverse-field Ising model we show how different quantum effects, such as quantum coherence and correlations, contribute to improving the performance in temporal tasks, as measured by the Information Processing Capacity. Additionally, we critically assess the impact of finite measurement resources and noise on the reservoir's dynamics in different regimes, quantifying the limited ability to exploit quantum effects for increasing damping and noise strengths. Our results reveal a monotonic relationship between reservoir performance and coherence, along with the importance of quantum effects in the ergodic regime., A.P. acknowledges the support of the European Commission FET-Open project AVaQus (GA 899561), the Agencia de Gestió d’Ajuts Universitaris i de Recerca through the DI grant (No. DI74) and the Spanish Ministry of Science and Innovation through the DI grant (No. DIN2020-011168). We acknowledge the Spanish State Research Agency, through the María de Maeztu project CEX2021-001164-M, through the COQUSY project PID2022-140506NB-C21 and -C22, and the INFOLANET project PID2022-139409NB-I00, all funded by MCIU/AEI/10.13039/501100011033 and FEDER, UE. This work was also supported by the Ministry for Digital Transformation and of Civil Service of the Spanish Government through the QUANTUM ENIA project call - Quantum Spain project, and by the European Union through the Recovery, Transformation and Resilience Plan - NextGenerationEU within the framework of the Digital Spain 2026 Agenda. G.L.G. is funded by the Spanish MEFP/MiU and co-funded by the University of the Balearic Islands through the Beatriz Galindo program (BG20/00085). R.M.P. acknowledges the QCDI project funded by the Spanish Government., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Neural networks with quantum states of light

  • Labay-Mora, Adrià
  • García-Beni, Jorge
  • Giorgi, Gian Luca
  • Soriano, Miguel C.
  • Zambrini, Roberta
Quantum optical networks are instrumental to address fundamental questions and enable applications ranging from communication to computation and, more recently, machine learning. In particular, photonic artificial neural networks offer the opportunity to exploit the advantages of both classical and quantum optics. Photonic neuro-inspired computation and machine learning have been successfully demonstrated in classical settings, while quantum optical networks have triggered breakthrough applications such as teleportation, quantum key distribution and quantum computing. We present a perspective on the state of the art in quantum optical machine learning and the potential advantages of artificial neural networks in circuit designs and beyond, in more general analogue settings characterised by recurrent and coherent complex interactions. We consider two analogue neuro-inspired applications, namely quantum reservoir computing and quantum associative memories, and discuss the enhanced capabilities offered by quantum substrates, highlighting the specific role of light squeezing in this context., We acknowledge the Spanish State Research Agency, through the Maria de Maeztu project CEX2021−001164-M funded by the MCIN/AEI/10.13039/501100011033, through the COQUSY project PID2022−140506NB-C21 and -C22 funded by MCIN/AEI/10.13039/501100011033 and through the INFOLANET project PID2022−139409NB-I00 funded by MCIN/AEI/10.13039/501100011033; MINECO through the QUANTUM SPAIN project and EU through the RTRP - NextGenerationEU within the framework of the Digital Spain 2025 Agenda. G.L.G. is funded by the Spanish Ministerio de Educacion y Formacion Profesional/Ministerio de Universidades and co-funded by the University of the Balearic Islands through the Beatriz Galindo program (BG20/00085). A.L.M. is funded by the University of the Balearic Islands through the project BGRH-UIB−2021. J.G.B. is funded by the Conselleria d’Educació, Universitat i Recerca of the Government of the Balearic Islands with grant code FPI/036/2020., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Temporal pattern generation with tunable repetition rate using semiconductor laser periodic dynamics

  • Argyris, Apostolos
In this work, a long-cavity semiconductor laser subject to optical feedback is exploited to generate repetitive temporal patterns with enhanced intra-pattern sample diversity. Stable limit cycle dynamics characterized by multiple frequency harmonics are experimentally demonstrated by considering a 2 m external cavity with appropriate optical feedback conditions. This simple configuration can enable stable and continuous generation of periodic waveforms with a tunable repetition rate ranging from 3.28 to 4.21 GHz. Distinct, highly consistent temporal patterns are obtained by applying high-pass filtering to adjust the relative power of the harmonics. The resulting system operates as a physical waveform generator capable of producing diverse and repeatable signal patterns, making it well-suited for use in the masking stage of time delay reservoir computing architectures., This work was supported by the Program for Centers and Units of Excellence in R&D María de Maeztu under the project CEX2021-001164-M, and the project INFOLANET PID2022-139409NB-I00, both funded by MCIN/AEI/10.13039/501100011033., With funding from the Spanish government through the "María de Maeztu Unit of Excellence" accreditation (CEX2021-001164-M), No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Experimental memory control in continuous variable optical quantum reservoir computing (v3)

  • Paparelle, Iris
  • Henaff, Johan
  • García Beni, Jorge
  • Gillet, Émilie
  • Montesinos, Daniel
  • Giorgi, Gian Luca
  • Soriano, Miguel C.
  • Zambrini, Roberta
  • Parigi, Valentina
24 pages, 10 figures, Quantum reservoir computing (QRC) offers a promising framework for online quantum-enhanced machine learning tailored to temporal tasks, yet practical implementations with native memory capabilities remain limited. Here, we demonstrate an optical QRC platform based on deterministically generated multimode squeezed states, exploiting both spectral and temporal multiplexing in a fully continuous-variable (CV) setting, and enabling controlled fading memory. Data is encoded via programmable phase shaping of the pump in an optical parametric process and retrieved through mode-selective homodyne detection. Real-time memory is achieved through feedback using electro-optic phase modulation, while long-term dependencies are achieved via spatial multiplexing. This architecture with minimal post-processing performs nonlinear temporal tasks, including parity checking and chaotic signal forecasting, with results corroborated by a high-fidelity Digital Twin. We show that leveraging the entangled multimode structure significantly enhances the expressivity and memory capacity of the quantum reservoir. This work establishes a scalable photonic platform for quantum machine learning, operating in CV encoding and supporting practical quantum-enhanced information processing., This work was supported by the European Research Council under the Consolidator Grant COQCOoN (Grant No. 820079) and by Agence Nationale de la Recherche (OQuLus, ANR-22-PETQ-0013). We acknowledge the Spanish State Research Agency, through the María de Maeztu project CEX2021-001164-M, through the COQUSY project PID2022-140506NB-C21 and -C22, through the INFOLANET project PID2022-139409NB-I00, and through the QuantCom project CNS2024-154720, all funded by MCIU/AEI/10.13039/501100011033; the project is funded under the Quantera II programme that has received funding from the EU’s H2020 research and innovation programme under the GA No 101017733, and from the Spanish State Research Agency, PCI2024-153410 funded by MCIU/ AEI/10.13039/50110001103; MINECO through the QUANTUM SPAIN project, and EU through the RTRP - NextGenerationEU within the framework of the Digital Spain 2025 Agenda; CSIC’s Quantum Technologies Platform (QTEP). J.G-B. is funded by the Conselleria d’Educaci´o, Universitat i Recerca of the Government of the Balearic Islands with grant code FPI/036/2020 and D.M. by the ”la Caixa” Foundation (ID 100010434), code LCF/BQ/DR24/12080033., With funding from the Spanish government through the "Maria de Maeztu Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Experimental memory control in continuous variable optical quantum reservoir computing (v1)

  • Paparelle, Iris
  • Henaff, Johan
  • García Beni, Jorge
  • Gillet, Émilie
  • Montesinos, Daniel
  • Giorgi, Gian Luca
  • Soriano, Miguel C.
  • Zambrini, Roberta
  • Parigi, Valentina
Quantum reservoir computing (QRC) offers a promising framework for online quantum-enhanced machine learning tailored to temporal tasks, yet practical implementations with native memory capabilities remain limited. Here, we demonstrate an optical QRC platform based on deterministically generated multimode squeezed states, exploiting both spectral and temporal multiplexing in a fully continuous-variable (CV) setting, and enabling controlled fading memory. Data is encoded via programmable phase shaping of the pump in an optical parametric process and retrieved through mode-selective homodyne detection. Real-time memory is achieved through feedback using electro-optic phase modulation, while long-term dependencies are achieved via spatial multiplexing. This architecture with minimal post-processing performs nonlinear temporal tasks, including parity checking and chaotic signal forecasting, with results corroborated by a high-fidelity Digital Twin. We show that leveraging the entangled multimode structure significantly enhances the expressivity and memory capacity of the quantum reservoir. This work establishes a scalable photonic platform for quantum machine learning, operating in CV encoding and supporting practical quantum-enhanced information processing., This work was supported by the European Research Council under the Consolidator Grant COQCOoN (Grant No. 820079) and by Agence Nationale de la Recherche (OQuLus, ANR-22-PETQ-0013). We acknowledge the Spanish State Research Agency, through the María de Maeztu project CEX2021-001164-M, through the COQUSY project PID2022-140506NB-C21 and -C22, through the INFOLANET project PID2022-139409NB-I00, and through the QuantCom project CNS2024-154720, all funded by MCIU/AEI/10.13039/501100011033; the project is funded under the Quantera II programme that has received funding from the EU’s H2020 research and innovation programme under the GA No 101017733, and from the Spanish State Research Agency, PCI2024-153410 funded by MCIU/ AEI/10.13039/50110001103; MINECO through the QUANTUM SPAIN project, and EU through the RTRP - NextGenerationEU within the framework of the Digital Spain 2025 Agenda; CSIC’s Quantum Technologies Platform (QTEP). J.G-B. is funded by the Conselleria d’Educaci´o, Universitat i Recerca of the Government of the Balearic Islands with grant code FPI/036/2020 and D.M. by the ”la Caixa” Foundation (ID 100010434), code LCF/BQ/DR24/12080033., With funding from the Spanish government through the "Maria de Maeztu Centre of Excellence" accreditation (CEX2021-001164-M)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Experimental memory control in continuous variable optical quantum reservoir computing (v2)

  • Paparelle, Iris
  • Henaff, Johan
  • García Beni, Jorge
  • Gillet, Émilie
  • Montesinos, Daniel
  • Giorgi, Gian Luca
  • Soriano, Miguel C.
  • Zambrini, Roberta
  • Parigi, Valentina
Quantum reservoir computing (QRC) offers a promising framework for online quantum-enhanced machine learning tailored to temporal tasks, yet practical implementations with native memory capabilities remain limited. Here, we demonstrate an optical QRC platform based on deterministically generated multimode squeezed states, exploiting both spectral and temporal multiplexing in a fully continuous-variable (CV) setting, and enabling controlled fading memory. Data is encoded via programmable phase shaping of the pump in an optical parametric process and retrieved through mode-selective homodyne detection. Real-time memory is achieved through feedback using electro-optic phase modulation, while long-term dependencies are achieved via spatial multiplexing. This architecture with minimal post-processing performs nonlinear temporal tasks, including parity checking and chaotic signal forecasting, with results corroborated by a high-fidelity Digital Twin. We show that leveraging the entangled multimode structure significantly enhances the expressivity and memory capacity of the quantum reservoir. This work establishes a scalable photonic platform for quantum machine learning, operating in CV encoding and supporting practical quantum-enhanced information processing., This work was supported by the European Research Council under the Consolidator Grant COQCOoN (Grant No. 820079) and by Agence Nationale de la Recherche (OQuLus, ANR-22-PETQ-0013). We acknowledge the Spanish State Research Agency, through the María de Maeztu project CEX2021-001164-M, through the COQUSY project PID2022-140506NB-C21 and -C22, through the INFOLANET project PID2022-139409NB-I00, and through the QuantCom project CNS2024-154720, all funded by MCIU/AEI/10.13039/501100011033; the project is funded under the Quantera II programme that has received funding from the EU’s H2020 research and innovation programme under the GA No 101017733, and from the Spanish State Research Agency, PCI2024-153410 funded by MCIU/ AEI/10.13039/50110001103; MINECO through the QUANTUM SPAIN project, and EU through the RTRP - NextGenerationEU within the framework of the Digital Spain 2025 Agenda; CSIC’s Quantum Technologies Platform (QTEP). J.G-B. is funded by the Conselleria d’Educaci´o, Universitat i Recerca of the Government of the Balearic Islands with grant code FPI/036/2020 and D.M. by the ”la Caixa” Foundation (ID 100010434), code LCF/BQ/DR24/12080033., With funding from the Spanish government through the "Maria de Maeztu Centre of Excellence" accreditation (CEX2021-001164-M)., No