Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 4, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

1.2K

A decentralized training algorithm for Echo State Networks in distributed big data applications.

Simone Scardapane1, Dianhui Wang2, Massimo Panella1

  • 1Department of Information Engineering, Electronics and Telecommunications (DIET), "Sapienza" University of Rome, Via Eudossiana 18, 00184 Rome, Italy.

Neural Networks : the Official Journal of the International Neural Network Society
|September 6, 2015
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Distributed Loads: Problem Solving01:21

Distributed Loads: Problem Solving

1.2K
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
1.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The Emerging Role of Explainable Artificial Intelligence in EEG-Based Autism Research: A Systematic Review.

NeuroSci·2026
Same author

CQD-Modified SrTiO<sub>3</sub> for Enhanced Photocatalytic CO<sub>2</sub> Reduction to Methane.

Materials (Basel, Switzerland)·2026
Same author

CaCO<sub>3</sub>/BiO<sub>2-x</sub>/CdS Composite with Rapid Photocatalytic Reduction of Cr(VI) Under Visible Light.

Nanomaterials (Basel, Switzerland)·2026
Same author

Smart Microfluidics: A curated dataset of microfluidic liposome formulations with cross-laboratory validation for machine-learning applications.

Data in brief·2026
Same author

A deep learning framework for comprehensive prediction of human RNA G-quadruplex-binding proteins.

Bioinformatics (Oxford, England)·2026
Same author

Recurrent Stochastic Configuration Networks With Hybrid Regularization for Nonlinear Dynamics Modeling.

IEEE transactions on cybernetics·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel decentralized training algorithm for Echo State Networks (ESNs), a type of recurrent neural network (RNN). The method enables efficient big data processing without central coordination or data sharing, outperforming centralized approaches.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Big Data Analytics

Background:

  • Big data presents challenges in volume, velocity, and heterogeneity.
  • Decentralized training is crucial for big data applications but underexplored for recurrent neural networks (RNNs).
  • Existing solutions often lack decentralized training for RNNs like Echo State Networks (ESNs).

Purpose of the Study:

  • To propose a novel decentralized training algorithm for Echo State Networks (ESNs).
  • To address the need for efficient big data inference in heterogeneous environments.
  • To enable distributed training without a central coordinating node or communication of training patterns.

Main Methods:

  • Developed a decentralized algorithm for Echo State Networks (ESNs).
Keywords:
Alternating Direction Method of MultipliersBig dataDistributed learningEcho State NetworkRecurrent neural network

Related Experiment Videos

Last Updated: Apr 4, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

1.2K
  • Utilized the Alternating Direction Method of Multipliers (ADMM) optimization procedure.
  • Formulated the algorithm using only local exchanges between neighboring agents.

    • Main Results:

    • The proposed algorithm enables decentralized training of ESNs.
    • It operates without a central coordinating node.
    • It does not require communication of training patterns, enhancing privacy and efficiency.
    • Experimental results show favorable comparisons with centralized implementations in speed, efficiency, and generalization accuracy on large datasets.

    Conclusions:

    • The novel ADMM-based algorithm facilitates efficient decentralized training of ESNs.
    • This approach is suitable for big data scenarios with technological constraints.
    • The method offers a competitive alternative to centralized training for RNNs.