Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

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 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