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 Concept Videos

Neural Regulation01:37

Neural Regulation

39.6K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.6K
Neural Circuits01:25

Neural Circuits

1.4K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.4K

You might also read

Related Articles

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

Sort by
Same author

Addressing Lignin Composition and Content via Arabidopsis Arogenate Dehydratase Knockout and Over-expression Genotypes.

Phytochemistry·2026
Same author

Polymer-regulated crystallization enables scalable, high-performance heterostructured perovskite luminescent optoelectronic fibers.

Science bulletin·2026
Same author

Confinement-Regulated Crystal Phase Engineering Enables Structured Semiconductor Fiber Systems for Plant Transpiration Dynamics Monitoring.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Photovoltaic arrays as ecological engineers: Microclimate-driven functional divergence for synergistic soil remediation in coal mining subsidence areas.

Bioresource technology·2026
Same author

Collaborative Hyperparameter Recommendation by Coupled Matrix Factorization With Kernel.

IEEE transactions on neural networks and learning systems·2026
Same author

Manganese-Chelating L-Serine Nanoarchitectures: Targeting Kidney Injury Molecule-1 for Reversing Renal Ischemia-Reperfusion Injury via Senescence Regulation.

Angewandte Chemie (International ed. in English)·2026

Related Experiment Video

Updated: Aug 11, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

10.0K

SPIDE: A purely spike-based method for training feedback spiking neural networks.

Mingqing Xiao1, Qingyan Meng2, Zongpeng Zhang3

  • 1National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, China.

Neural Networks : the Official Journal of the International Neural Network Society
|February 3, 2023
PubMed
Summary

We introduce spike-based implicit differentiation on the equilibrium state (SPIDE) for training spiking neural networks (SNNs) using only spike computations. This method enables energy-efficient SNN training with competitive performance on benchmark datasets.

Keywords:
Equilibrium stateNeuromorphic computingSpike-based training methodSpiking neural networks

More Related Videos

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.1K
Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

10.0K

Related Experiment Videos

Last Updated: Aug 11, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

10.0K
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.1K
Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

10.0K

Area of Science:

  • Neuromorphic Engineering
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Spiking neural networks (SNNs) offer energy-efficient computation inspired by the brain.
  • Current supervised SNN training methods often rely on non-spike-based computations, limiting efficiency.
  • There is a need for training methods that leverage SNNs' inherent event-driven, spike-based operations.

Purpose of the Study:

  • To develop a purely spike-based training method for SNNs.
  • To enable energy-efficient supervised learning on neuromorphic hardware.
  • To demonstrate the potential of spike-based implicit differentiation for SNN training.

Main Methods:

  • Introduced spike-based implicit differentiation on the equilibrium state (SPIDE).
  • Utilized ternary spiking neuron couples for spike-based implicit differentiation.
  • Implemented local weight updates using two-stage average firing rates.
  • Modified reset membrane potential to minimize approximation errors.

Main Results:

  • Achieved purely spike-based forward and backward passes for SNN training.
  • Demonstrated training of SNNs with flexible structures in few time steps and with firing sparsity.
  • Theoretical energy cost estimations indicate high potential efficiency.
  • Attained competitive results on MNIST, CIFAR-10, CIFAR-100, and CIFAR10-DVS datasets.

Conclusions:

  • SPIDE enables energy-efficient supervised training of SNNs using only spike-based computations.
  • The proposed method maintains competitive performance despite computational constraints.
  • This approach holds significant promise for efficient SNNs on neuromorphic hardware.