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

Integration of Synaptic Events01:28

Integration of Synaptic Events

Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
Neural Circuits01:25

Neural Circuits

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...

You might also read

Related Articles

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

Sort by
Same author

Z-scheme heterojunction based organic photoelectrochemical transistors for ultrasensitive methyl parathion detection.

Mikrochimica acta·2026
Same author

Multi-scale dynamic cooperative attention network for auditory attention detection.

Biomedical physics & engineering express·2026
Same author

Effects of Different Nutrient Management Regimes on Rice Yield and Nitrogen Uptake and Use Efficiency.

Plants (Basel, Switzerland)·2026
Same author

The association between maternal and paternal parenting styles and adolescents' overall mental problem: a longitudinal study.

BMC psychology·2026
Same author

Multi-omics-guided discovery of CYP5035 enables heterologous production and engineering of pachymic acid in yeast.

Journal of biological engineering·2026
Same author

Size-dependent lymphatic delivery of Gd-based MRI contrast agents: insights from <i>in vivo</i> studies.

Journal of materials chemistry. B·2026

Related Experiment Video

Updated: May 28, 2026

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

SE-SNN: Squeeze-and-Excitation-Enhanced Spiking Neural Networks with Learnable Neuron Dynamics for Event-Based

Chuang Liu1, Yang Chen1

  • 1School of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, China.

Biomimetics (Basel, Switzerland)
|May 26, 2026
PubMed
Summary

Spiking neural networks (SNNs) achieve higher accuracy on event-based vision tasks by integrating Squeeze-Excitation (SE) blocks and adaptive neuron models. This enhances representational capacity and temporal dynamics for efficient neuromorphic computing.

Keywords:
CIFAR10-DVSevent-based visionlearnable neuron dynamicsneuromorphic computingspiking neural networkssqueeze-and-excitation

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

Related Experiment Videos

Last Updated: May 28, 2026

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

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

Area of Science:

  • Neuromorphic Computing
  • Artificial Intelligence
  • Computer Vision

Background:

  • Spiking neural networks (SNNs) offer energy-efficient processing for neuromorphic computing, especially with dynamic vision sensors (DVSs).
  • Traditional SNNs face limitations in representational capacity and feature recalibration compared to artificial neural networks.
  • Addressing these limitations is crucial for advancing SNN performance in complex tasks.

Purpose of the Study:

  • To introduce SE-SNN, a novel SNN architecture incorporating Squeeze-Excitation (SE) blocks for enhanced channel-wise attention.
  • To develop a Robust Parametric Leaky Integrate-and-Fire (RobustPLIF) neuron model with adaptive temporal dynamics.
  • To improve the performance and efficiency of SNNs for event-based vision processing.

Main Methods:

  • Integration of SE blocks into deep residual SNNs, enabling attention without additional spike generation.
  • Implementation of a RobustPLIF neuron model with learnable membrane time constant (τ) and firing threshold (vth).
  • Training and evaluation of the proposed SE-SNN architecture on the CIFAR10-DVS dataset.

Main Results:

  • SE-SNN achieved 78.8% accuracy on the CIFAR10-DVS dataset with only 16 time steps.
  • The proposed model outperformed baseline SNNs in accuracy.
  • Ablation studies validated the significant contributions of SE blocks and learnable neuron parameters.

Conclusions:

  • The SE-SNN architecture effectively enhances representational capacity and temporal dynamics in SNNs.
  • The proposed model demonstrates superior performance and maintains biological plausibility and hardware efficiency.
  • SE-SNN represents a significant advancement in SNNs for energy-efficient neuromorphic computing.