Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Graded Potential

Graded Potential

Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...

You might also read

Related Articles

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

Sort by

Same author

Hedgehog signaling enhances the Schwann-like and nerve repair-supportive properties of ectomesenchymal stem cells.

Frontiers in neuroscience·2026

Same author

Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence.

Science advances·2026

Same author

An online packing strategy for high volume injection in sensitivity-enhanced UPLC-MS/MS analysis of 30 veterinary drugs in beef.

Journal of chromatography. A·2026

Same author

Biologically inspired spiking diffusion model with adaptive lateral selection mechanism.

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

Same author

Interpretable LightGBM model for predicting postoperative gastrointestinal hemorrhage in elderly hip fracture patients: leveraging systemic inflammation and medication exposures for personalized risk stratification.

BMC geriatrics·2026

Same author

Continual learning of multiple cognitive functions with a brain-inspired temporal development mechanism.

National science review·2026

Search research articles

Related Experiment Video

Updated: Jun 21, 2025

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

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

Published on: March 25, 2014

Directly training temporal Spiking Neural Network with sparse surrogate gradient.

Yang Li¹, Feifei Zhao¹, Dongcheng Zhao²

¹Brain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.

Neural Networks : the Official Journal of the International Neural Network Society

|July 16, 2024

Summary

This summary is machine-generated.

This study introduces Masked Surrogate Gradients (MSGs) and temporally weighted output (TWO) to improve Spiking Neural Network (SNN) training. These methods enhance SNN performance by balancing training effectiveness and gradient sparsity.

Keywords:

Direct Training Sparse Surrogate Gradient Spiking Neural Network Temporally Weighted Output

More Related Videos

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

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

Published on: November 12, 2019

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

Related Experiment Videos

Last Updated: Jun 21, 2025

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

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

Published on: March 25, 2014

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

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

Published on: November 12, 2019

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

Area of Science:

Artificial Intelligence
Computational Neuroscience
Machine Learning

Background:

Spiking Neural Networks (SNNs) offer energy-efficient, event-based computing.
Direct training of SNNs is challenging due to their all-or-none spiking nature.
Surrogate Gradients (SGs) enable SNN training but can reduce sparsity and performance.

Purpose of the Study:

To address the performance loss in SNNs caused by the reduced sparsity from surrogate gradient training.
To propose novel methods for effective and sparse training of SNNs.
To improve the generalization ability of Spiking Neural Networks.

Main Methods:

Analysis of direct training issues with surrogate gradients.
Introduction of Masked Surrogate Gradients (MSGs) to balance training effectiveness and gradient sparseness.
Implementation of a temporally weighted output (TWO) method for network decoding.

Main Results:

Masked Surrogate Gradients (MSGs) effectively balance training and gradient sparseness.
The temporally weighted output (TWO) method reinforces the importance of correct timesteps.
Combined MSG and TWO methods surpass state-of-the-art training techniques in experiments.

Conclusions:

The proposed MSG and TWO methods offer a superior approach for training Spiking Neural Networks.
These techniques improve SNN generalization and performance while maintaining desirable sparsity.
This work advances the practical application of SNNs in neuromorphic hardware.