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: Jun 8, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

SWAT: a spiking neural network training algorithm for classification problems.

John J Wade1, Liam J McDaid, Jose A Santos

  • 1Intelligent Systems Research Center, University of Ulster, School of Computing and Intelligent Systems, Derry, Northern Ireland, U.K. jj.wade@ulster.ac.uk

IEEE Transactions on Neural Networks
|September 30, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Toward microfluidic integration of respiratory and renal organ support in a single cartridge.

Artificial organs·2023
Same author

Long-Term Results of a Phase I/II Clinical Trial of Autologous Mesenchymal Stem Cell Therapy for Femoral Head Osteonecrosis.

Journal of clinical medicine·2023
Same author

Design and construction of three-dimensional physiologically-based vascular branching networks for respiratory assist devices.

Lab on a chip·2021
Same author

Field-Portable Microplastic Sensing in Aqueous Environments: A Perspective on Emerging Techniques.

Sensors (Basel, Switzerland)·2021
Same author

Extreme blood lactate rising after very short efforts in top-level track and field male sprinters.

Research in sports medicine (Print)·2021
Same author

ARDebug: An Augmented Reality Tool for Analysing and Debugging Swarm Robotic Systems.

Frontiers in robotics and AI·2021
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

The novel Synaptic Weight Association Training (SWAT) algorithm for spiking neural networks (SNNs) merges BCM and STDP learning rules. SWAT demonstrates high accuracy and generalization capabilities in classification tasks like ASR.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Artificial Intelligence

Background:

  • Spiking Neural Networks (SNNs) offer bio-inspired computation.
  • Existing training methods for SNNs face challenges in stability and efficiency.
  • The Bienenstock-Cooper-Munro (BCM) and Spike Timing Dependent Plasticity (STDP) rules are key learning mechanisms.

Purpose of the Study:

  • To introduce a new training algorithm, Synaptic Weight Association Training (SWAT), for SNNs.
  • To enhance the stability and performance of SNNs through a merged learning rule.
  • To evaluate SWAT's effectiveness on benchmark datasets and an Automatic Speech Recognition (ASR) system.

Main Methods:

  • SWAT merges the BCM learning rule with STDP, creating a unimodal weight distribution and stable plasticity.

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Related Experiment Videos

Last Updated: Jun 8, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

  • A single training neuron processes data from all classes, mapping weights to output neurons based on data similarities.
  • The SNN incorporates excitatory/inhibitory synapses for frequency routing and a variable threshold for refractory period simulation.

    • Main Results:

    • SWAT achieved high convergence accuracy: 95.5% (Iris training), 96.2% (Wisconsin training), 95.3% (Iris testing), and 96.7% (Wisconsin testing).
    • Noise experiments confirmed SWAT's good generalization capability.
    • In an isolated digit ASR system, SWAT achieved 98.875% training accuracy and 95.25% testing accuracy.

    Conclusions:

    • SWAT provides a stable and effective training method for SNNs.
    • The algorithm demonstrates strong performance on diverse classification tasks, including complex datasets and ASR.
    • SWAT offers a promising approach for advancing SNN applications in machine learning.