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 Videos

Spatial and temporal pattern analysis via spiking neurons

T Natschläger1, B Ruf

  • 1Institute for Theoretical Computer Science, Technische Universität Graz, Austria. tnatschl@igi.tu-graz.ac.at

Network (Bristol, England)
|December 23, 1998
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

First negative ion beam measurement by the Short-Time Retractable Instrumented Kalorimeter Experiment (STRIKE).

The Review of scientific instruments·2014
Same author

3D numerical simulations of negative hydrogen ion extraction using realistic plasma parameters, geometry of the extraction aperture and full 3D magnetic field map.

The Review of scientific instruments·2014
Same author

Treatment of severe, nonfulminant acute hepatitis B with lamivudine vs placebo: a prospective randomized double-blinded multicentre trial.

Journal of viral hepatitis·2013
Same author

Abnormal prefrontal activity subserving attentional control of emotion in remitted depressed patients during a working memory task with emotional distracters.

Psychological medicine·2011
Same author

Self-organization of spiking neurons using action potential timing.

IEEE transactions on neural networks·2008
Same author

[Polyuria].

Therapeutische Umschau. Revue therapeutique·2006
Same journal

Enhancing IoT security: A Creative Swagger Optimization algorithm for DDoS defence.

Network (Bristol, England)·2026
Same journal

Parametric optimization for electrical discharge diamond grinding (EDDG) system using dual approach.

Network (Bristol, England)·2025
Same journal

A novel lung cancer diagnosis model using hybrid convolution (2D/3D)-based adaptive DenseUnet with attention mechanism.

Network (Bristol, England)·2025
Same journal

Hybrid optimization enabled Eff-FDMNet for Parkinson's disease detection and classification in federated learning.

Network (Bristol, England)·2025
Same journal

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same journal

Layer modified residual Unet++ for speech enhancement using Aquila Black widow optimizer algorithm.

Network (Bristol, England)·2025
See all related articles

This study introduces a biologically plausible learning method for spiking neural networks to compute radial basis functions (RBFs). It enables unsupervised clustering, feature extraction, and temporal sequence recognition in dynamic, high-dimensional environments.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Artificial neural networks

Background:

  • Spiking neurons process information using temporal coding.
  • Radial Basis Functions (RBFs) are crucial for clustering and function approximation.
  • Learning in spiking neural networks often requires complex, non-local information.

Purpose of the Study:

  • To develop a biologically plausible learning rule for spiking neurons to compute RBFs.
  • To enable unsupervised clustering and feature extraction in high-dimensional spaces using spiking neural networks.
  • To demonstrate the model's capability in recognizing distorted temporal sequences.

Main Methods:

  • Utilizing local information, specifically the time difference between pre- and postsynaptic spikes, to learn neuron delays.

Related Experiment Videos

  • Implementing a network of spiking neurons capable of dynamic adaptation to changing environments.
  • Applying the learned RBF neurons for feature extraction and temporal sequence recognition.

    • Main Results:

    • A novel, local learning algorithm for RBF computation in spiking neurons was developed.
    • The algorithm facilitates biologically plausible, unsupervised clustering in dynamic, high-dimensional input spaces.
    • The model successfully performs feature extraction, identifying relevant input coordinates.
    • Robust recognition of distorted temporal sequences was achieved.

    Conclusions:

    • Local learning rules can effectively train spiking neurons for complex computational tasks like RBFs.
    • This approach offers a biologically plausible mechanism for unsupervised learning and feature extraction in neural systems.
    • The model demonstrates significant potential for applications in pattern recognition and sequence analysis, even with noisy or distorted inputs.