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

SpikeCell: a deterministic spiking neuron.

C Godin1, M B Gordon, J D Muller

  • 1DRFMC/SPSMS, CEA Grenoble, 17 av. des Martyrs, 38054 Grenoble Cedex 09, France.

Neural Networks : the Official Journal of the International Neural Network Society
|December 16, 2003
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

Correction to: Oral octreotide capsules for the treatment of acromegaly: comparison of 2 phase 3 trial results.

Pituitary·2021
Same author

Oral octreotide capsules for the treatment of acromegaly: comparison of 2 phase 3 trial results.

Pituitary·2021
Same author

A Multi-feature Fuzzy Index to Assess Stress Level from Bio-signals.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2018
Same author

A multi-scale model of the interplay between cell signalling and hormone transport in specifying the root meristem of Arabidopsis thaliana.

Journal of theoretical biology·2016
Same author

In vivo quantitative NMR imaging of fruit tissues during growth using Spoiled Gradient Echo sequence.

Magnetic resonance imaging·2014
Same author

mRNA of luteal genes associated with progesterone synthesis, maintenance, and apoptosis in dairy heifers and lactating dairy cows.

Animal reproduction science·2010
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
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

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

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

This study introduces a spiking neuron model that mimics static neurons, enabling efficient hardware implementation for neural networks. This model demonstrates robustness and achieves comparable accuracy to traditional networks.

Area of Science:

  • Computational Neuroscience
  • Hardware Implementation of Neural Networks

Background:

  • Traditional artificial neural networks often use static neurons with sigmoidal activation functions.
  • Implementing these networks in hardware can be resource-intensive.

Purpose of the Study:

  • To present a novel spiking neuron model that emulates static neurons.
  • To enable efficient hardware implementations of feedforward neural networks.
  • To validate the model's performance on recognition and classification tasks.

Main Methods:

  • Developed a spiking neuron model that replicates the output of static neurons.
  • Integrated the model into feedforward networks trained with classical algorithms like back-propagation.
  • Proposed and evaluated a digital architecture for hardware implementation.

Related Experiment Videos

  • Tested the model on handwritten digit recognition and image classification.

    • Main Results:

    • The spiking neuron model requires 10 times less chip area compared to static neurons.
    • Network accuracy improves over time, matching static networks after sufficient integration.
    • The model exhibits resilience to single errors in spike trains and process interruptions.

    Conclusions:

    • The proposed spiking neuron model offers a significant reduction in hardware footprint.
    • It provides a robust and efficient alternative for implementing neural networks in hardware.
    • The model achieves high accuracy and is suitable for tasks like digit recognition and image classification.