Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 15
Encontrada(s) 1 página(s)

Docta Complutense
Publicación Artículo científico (JournalArticle)

nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift

  • Susi, Gianluca
  • Antón Toro, Luis Fernando
  • Maestu Unturbe, Fernando
  • Pereda, Ernesto
  • Mirasso, Claudio
The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift

  • Susi, Gianluca
  • Antón-Toro, Luis F.
  • Maestú, Fernando
  • Pereda, Ernesto
  • Mirasso, Claudio R.
The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods., LA-T acknowledges financial support by UCM-SANTANDER scholarship to PhD students (Ref. C2017). FM acknowledges the Community of Madrid through the project Madrid Neurocentro (B2017/BMD-3760). EP and CM acknowledge support from MINECO and Ministerio de Ciencia e Innovación (Spain) through projects TEC2016-80063-C3 and PID2019-111537GB-C22/AEI/10.13039/501100011033. The work of CM is partially supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No. 899265-ADOPD. CM acknowledges the Spanish State Research Agency, through the María de Maeztu Program for Units of Excellence in R&D (MDM-2017-0711)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Unveiling the role of plasticity rules in reservoir computing

  • Morales, Guillermo B.
  • Mirasso, Claudio R.
  • Soriano, Miguel C.
Reservoir Computing (RC) is an appealing approach in Machine Learning that combines the high computational capabilities of Recurrent Neural Networks with a fast and easy training method. Likewise, successful implementation of neuro-inspired plasticity rules into RC artificial networks has boosted the performance of the original models. In this manuscript, we analyze the role that plasticity rules play on the changes that lead to a better performance of RC. To this end, we implement synaptic and non-synaptic plasticity rules in a paradigmatic example of RC model: the Echo State Network. Testing on nonlinear time series prediction tasks, we show evidence that improved performance in all plastic models are linked to a decrease of the pair-wise correlations in the reservoir, as well as a significant increase of individual neurons ability to separate similar inputs in their activity space. Here we provide new insights on this observed improvement through the study of different stages on the plastic learning. From the perspective of the reservoir dynamics, optimal performance is found to occur close to the so-called edge of instability. Our results also show that it is possible to combine different forms of plasticity (namely synaptic and non-synaptic rules) to further improve the performance on prediction tasks, obtaining better results than those achieved with single-plasticity models., This work was supported by the Ministerio de Ciencia e Innovación (Spain) through projects PID2019-111537GB-C22/AEI/10.13039/501100011033 and PID2019-109094GB-C22/AEI/10.13039/501100011033, and by the European Union's Horizon 2020 research and innovation programme under grant agreement No. 899265 (ADOPD). 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). The work of MCS has been supported by the Spanish Ministerio de Ciencia, Innovación y Universidades, la Agencia Estatal de Investigación, the European Social Fund and the University of the Balearic Islands through a ”Ramón y Cajal” Fellowship (RYC-2015–18140). GBM has been partly supported by the Spanish National Research Council via a JAE Intro fellowship (JAEINT18_EX_0684)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

Optical dendrites for spatio-temporal computing with few-mode fibers

  • Ortín González, Silvia
  • Soriano, Miguel C.
  • Fischer, Ingo
  • Mirasso, Claudio R.
  • 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., Multimode fibers have been recently considered for optical computing, by exploiting the complex spatial and spatio-temporal transformation at the fiber end. Mimicking the dendrites of real neurons, we consider here the spatial modes that propagate with different group velocities along the fiber as different dendritic branches. The multimode fiber plays the role of an optical dendritic unit (ODU) and the signals obtained from the different dendritic branches are temporally mixed and used for spatio-temporal information processing. We numerically demonstrate the use of a step-index, few mode fiber (FMF) as a linear computing element, in a spatio-temporal coincidence detector that operates at 40 Gb/s data encoding rate. We evaluate this detector as a linear classifier in header recognition and bit counting tasks., The authors acknowledge the support of the European Union's H2020 research and innovation programme under grant agreement No. 899265 (ADOPD)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Microring resonators with external optical feedback for time delay reservoir computing

  • Donati, Giovanni
  • Mirasso, Claudio R.
  • Mancinelli, Mattia
  • Pavesi, Lorenzo
  • Argyris, Apostolos
Microring resonators (MRRs) are a key photonic component in integrated devices, due to their small size, low insertion losses, and passive operation. While the MRRs have been established for optical filtering in wavelength-multiplexed systems, the nonlinear properties that they can exhibit give rise to new perspectives on their use. For instance, they have been recently considered for introducing optical nonlinearity in photonic reservoir computing systems. In this work, we present a detailed numerical investigation of a silicon MRR operation, in the presence of external optical feedback, in a time delay reservoir computing scheme. We demonstrate the versatility of this compact, passive device, by exploiting different operating regimes and solving computing tasks with diverse memory requirements. We show that when large memory is required, as it occurs in the Narma 10 task, the MRR nonlinearity does not play a significant role when the photodetection nonlinearity is involved, while the contribution of the external feedback is significant. On the contrary, for computing tasks such as the Mackey-Glass and the Santa Fe chaotic timeseries prediction, the MRR and the photodetection nonlinearities contribute both to efficient computation. The presence of optical feedback improves the prediction of the Mackey-Glass timeseries while it plays a minor role in the Santa Fe timeseries case., The work of G.D., C.R.M., and A.A. was partially supported by 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. A.A. and C.R.M. acknowledge the support from the European Union's Horizon 2020 Future and Emerging Technologies program (Grant Agreement No. 899265, ADOPD), and also the support from the Ministerio de Ciencia e Innovación through projects PID2019-111537GB-C21/AEI/10.13039/501100011033 and PID2019-111537GB-C22/AEI/10.13039/501100011033, respectively. G.D., M.M., and L.P. also acknowledge the funding support of this work under the European Research Council (ERC) and the European Union's Horizon 2020 research and innovation programme (Grant Agreement No. 788793, BACKUP)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Microring resonators with external optical feedback for time delay reservoir computing

  • Donati, Giovanni
  • Mirasso, Claudio R.
  • Mancinelli, Mattia
  • Pavesi, Lorenzo
  • Argyris, Apostolos
Microring resonators (MRRs) are a key photonic component in integrated devices, due to their small size, low insertion losses, and passive operation. While the MRRs have been established for optical filtering in wavelength-multiplexed systems, the nonlinear properties that they can exhibit give rise to new perspectives on their use. For instance, they have been recently considered for introducing optical nonlinearity in photonic reservoir computing systems. In this work, we present a detailed numerical investigation of a silicon MRR operation, in the presence of external optical feedback, in a time delay reservoir computing scheme. We demonstrate the versatility of this compact, passive device, by exploiting different operating regimes and solving computing tasks with diverse memory requirements. We show that when large memory is required, as it occurs in the Narma 10 task, the MRR nonlinearity does not play a significant role when the photodetection nonlinearity is involved, while the contribution of the external feedback is significant. On the contrary, for computing tasks such as the Mackey-Glass and the Santa Fe chaotic timeseries prediction, the MRR and the photodetection nonlinearities contribute both to efficient computation. The presence of optical feedback improves the prediction of the Mackey-Glass timeseries while it plays a minor role in the Santa Fe timeseries case., The work of G.D., C.R.M., and A.A. was partially supported by 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. A.A. and C.R.M. acknowledge the support from the European Union's Horizon 2020 Future and Emerging Technologies program (Grant Agreement No. 899265, ADOPD), and also the support from the Ministerio de Ciencia e Innovación through projects PID2019-111537GB-C21/AEI/10.13039/501100011033 and PID2019-111537GB-C22/AEI/10.13039/501100011033, respectively. G.D., M.M., and L.P. also acknowledge the funding support of this work under the European Research Council (ERC) and the European Union's Horizon 2020 research and innovation programme (Grant Agreement No. 788793, BACKUP)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Optical dendrites for spatio-temporal computing with few-mode fibers [Invited]

  • Ortín González, Silvia
  • Soriano, Miguel C.
  • Fischer, Ingo
  • Mirasso, Claudio R.
  • Argyris, Apostolos
Multimode fibers have been extensively used in short-range communication systems and optical imaging. More recently, they have been considered for optical computing by exploiting the complex spatial and spatio-temporal transformation at the fiber end. Mimicking the dendrites of real neurons, we consider here the spatial modes that propagate with different group velocities along the fiber as different dendritic branches. The multimode fiber plays the role of an optical dendritic unit and the signals obtained from the different dendritic branches are temporally mixed and used for spatio-temporal information processing. We numerically demonstrate the use of a few-mode, step-index fiber as a linear computing element in an ultra-fast spatio-temporal coincidence detector that operates at 40 Gb/s data encoding rate. We evaluate this detector as a linear classifier in header recognition and bit counting tasks., Horizon 2020 Framework Programme (899265); Agencia Estatal de Investigación (PID2019-109094GB-C21, -C22/AEI /10.13039/501100011033, PID2019-111537GB-C21, MDM-2017-0711,MCIN/AEI/10.13039/501100011033)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación 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
Publicación 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
Publicación 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
Publicación 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
Publicación Artículo científico (JournalArticle)

Implementation of input correlation learning with an optoelectronic dendritic unit

  • Ortín González, Silvia
  • Soriano, Miguel C.
  • Tetzlaff, Christian
  • Wörgötter, Florentin
  • Fischer, Ingo
  • Mirasso, Claudio R.
  • Argyris, Apostolos
The implementation of machine learning concepts using optoelectronic and photonic components is rapidly advancing. Here, we use the recently introduced notion of optical dendritic structures, which aspires to transfer neurobiological principles to photonics computation. In real neurons, plasticity—the modification of the connectivity between neurons due to their activity—plays a fundamental role in learning. In the current work, we investigate theoretically and experimentally an artificial dendritic structure that implements a modified Hebbian learning model, called input correlation (ICO) learning. The presented optical fiber-based dendritic structure employs the summation of the different optical intensities propagating along the optical dendritic branches and uses Gigahertz-bandwidth modulation via semiconductor optical amplifiers to apply the necessary plasticity rules. In its full deployment, this optoelectronic ICO learning analog can be an efficient hardware platform for ultra-fast control., The authors acknowledge the support of the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 899265 (ADOPD), and the fruitful discussions with Robert Legenstein and the rest scientific collaborators that participate in this project., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Experimental multi-bit header classification at 28.5 Gb/s with step-index few-mode fibers

  • Pfluger, Moritz
  • Ortín González, Silvia
  • Leininger, Lars
  • Mirasso, Claudio R.
  • Argyris, Apostolos
In analog computing, multimode fibers (MMFs) have been explored for their potential in performing computations by exploiting the inherent parallelism of light propagation through different transverse modes. However, traditional approaches using MMFs encounter challenges due to limitations in spatial-domain encoding, which limit computational speed and accuracy. Innovative research seeks to overcome these limitations, by leveraging novel techniques in temporal encoding and employing step-index few-mode fibers (FMFs), and enhance the computational capabilities of analog systems. In this work, we consider a 13 m FMF to implement up to 7-bit header classification at 28.5 Gb/s, when utilizing the information that is included in only one-bit duration. By activating a small number of spatial modes with proper dispersive optical characteristics, we are able to limit the complexity of the spatial transformation and solve such computing tasks efficiently. The selective activation of supported modes is performed by testing varying input displacement conditions between the optical beam encoding information and the FMF input tip. At the output of the fiber, we obtain multiple time series that correspond to different spatial sub-patterns of the output beam overall pattern. Finally, we train a logistic regression classifier that uses samples from these time series, and evaluate its performance in classification tasks. Notably, even in the presence of inter-header interference, our system achieves successful 6-bit header classification - a feat unattainable with conventional step-index MMFs., The authors appreciate the fruitful discussions with Miguel C. Soriano, Ingo Fischer and all the scientific collaborators within the European Union’s Horizon 2020 research and innovation programme ADOPD (grant agreement 899265). They also acknowledge the support from the Program for Centres and Units of Excellence in R&D, María de Maeztu project CEX2021-001164-M/10.13039/501100011033., 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 Artículo científico (JournalArticle)

Experimental Multi-Bit Header Classification at 28.5 Gb/s With Step-Index Few-Mode Fibers

  • Pfluger, Moritz
  • Ortín González, Silvia
  • Leininger, Lars
  • Mirasso, Claudio R.
  • Argyris, Apostolos
In analog computing, multimode fibers (MMFs) have been explored for their potential in performing computations by exploiting the inherent parallelism of light propagation through different transverse modes. However, traditional approaches using MMFs encounter challenges due to limitations in spatial-domain encoding, which limit computational speed and accuracy. Innovative research seeks to overcome these limitations, by leveraging novel techniques in temporal encoding and employing step-index few-mode fibers (FMFs), and enhance the computational capabilities of analog systems. In this work, we consider a 13 m FMF to implement up to 7-bit header classification at 28.5 Gb/s, when utilizing the information that is included in only one-bit duration. By activating a small number of spatial modes with proper dispersive optical characteristics, we are able to limit the complexity of the spatial transformation and solve this computing task efficiently. The selective activation of supported modes is performed by testing varying input displacement conditions between the optical beam encoding information and the FMF input tip. At the output of the fiber, we obtain multiple time series that correspond to different spatial sub-patterns of the output beam overall pattern. Finally, we train a logistic regression classifier that uses samples from these time series, and evaluate its performance in classification tasks. Notably, even in the presence of inter-header interference, our system achieves successful 6-bit header classification - a feat unattainable with conventional step-index MMFs., This work has been funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 899265 (ADOPD) and from the Program for Centres and Units of Excellence in R&D, Marí a de Maeztu project 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
Publicación Artículo científico (JournalArticle)

Temperature stabilization with Hebbian learning using an autonomous optoelectronic dendritic unit

  • Ortín González, Silvia
  • Pflüger, M.
  • Argyris, Apostolos
The integration of machine learning with photonic and optoelectronic components is progressing rapidly, offering the potential for high-speed bio-inspired computing platforms. In this work, we employ an experimental fiber-based dendritic structure with adaptive plasticity for a learning-and-control virtual task. Specifically, we develop a closed-loop controller embedded in a single-mode fiber optical dendritic unit (ODU) that incorporates Hebbian learning principles, and we test it in a hypothetical temperature stabilization task. Our optoelectronic system operates at 1 GHz signaling and sampling rates and applies plasticity rules through the direct modulation of semiconductor optical amplifiers. Although the input correlation (ICO) learning rule we consider here is computed digitally from the experimental output of the optoelectronic system, this output is fed back into the plastic properties of the ODU physical substrate, enabling autonomous learning. In this specific configuration, we utilize only three plastic dendritic optical branches with exclusively positive weighting. We demonstrate that, despite variations in the physical system's parameters, the application of the ICO learning rule effectively mitigates temperature disturbances, ensuring robust performance. These results encourage an all-hardware solution, where optimizing feedback loop speed and embedding the ICO rule will enable continuous stabilization, finalizing a real-time platform operating at up to 1 GHz., This work was supported by the European Union’s Horizon 2020 Research and Innovation Programme under Grant 899265 (ADOPD), the Program for Centres and Units of Excellence in R&D María de Maeztu under Project CEX2021-001164-M funded by MCIN/AEI/10.13039/501100011033, and the project INFOLANET PID2022-139409NB-I00 funded by MCIN/AEI/10.13039/501100011033. The authors appreciate the fruitful discussions with Claudio R. Mirasso, Miguel C. Soriano, Ingo Fischer, Florentin Wörgötter, and Christian Tetzlaff., With funding from the Spanish government through the "María de Maeztu Unit of Excellence" accreditation (CEX2021-001164-M), Peer reviewed