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

A spiking neural network architecture for nonlinear function approximation.

N Iannella1, A D Back

  • 1Brain Science Institute, RIKEN, Saitama, Japan. angelo@postman.riken.go.jp

Neural Networks : the Official Journal of the International Neural Network Society
|October 23, 2001
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

FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling.

Neural computation·2019
Same author

Selecting inputs for modeling using normalized higher order statistics and independent component analysis.

IEEE transactions on neural networks·2008
Same author

A first application of independent component analysis to extracting structure from stock returns.

International journal of neural systems·1997
Same author

Face recognition: a convolutional neural-network approach.

IEEE transactions on neural networks·1997
Same author

On the distribution of performance from multiple neural-network trials.

IEEE transactions on neural networks·1997
Same author

Locally recurrent globally feedforward networks: a critical review of architectures.

IEEE transactions on neural networks·1994
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

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

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

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

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

This study introduces a novel spiking neural network architecture capable of universal function approximation. This biologically inspired model uses integrate-and-fire units and delays for robust signal processing.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Multilayer perceptrons (MLPs) are known for universal approximation but use continuous signals.
  • Biological neurons use spike trains, offering robust signaling in noisy environments.
  • Spiking neural networks (SNNs) bridge biological realism and computational power.

Purpose of the Study:

  • To investigate architectures for universal function approximation in SNNs.
  • To propose a novel SNN architecture capable of approximating real-valued functions.

Main Methods:

  • Developed a spiking neural network architecture.
  • Incorporated integrate-and-fire units and signal delays.
  • Analyzed the network's function approximation capabilities.

Related Experiment Videos

Main Results:

  • The proposed SNN architecture demonstrates universal function approximation.
  • The network can approximate real-valued functions to a specified accuracy.
  • The architecture leverages biologically plausible components.

Conclusions:

  • Spiking neural networks can achieve universal function approximation.
  • The proposed architecture offers a biologically plausible and robust approach to function approximation.
  • This work advances the understanding of SNN capabilities for complex computational tasks.