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

You might also read

Related Articles

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

Sort by
Same author

Magnetoacoustic tomography with magnetic induction for high-resolution bioimepedance imaging through vector source reconstruction under the static field of MRI magnet.

Medical physics·2014
Same author

Hollow superparamagnetic PLGA/Fe3O4 composite microspheres for lysozyme adsorption.

Nanotechnology·2014
Same author

[A bird's eye view of the algorithms and software packages for reconstructing phylogenetic trees].

Dong wu xue yan jiu = Zoological research·2014
Same author

Functional and biodegradable dendritic macromolecules with controlled architectures as nontoxic and efficient nanoscale gene vectors.

Biotechnology advances·2014
Same author

[Effects of artificial vegetation on the spatial heterogeneity of soil moisture and salt in coastal saline land of Chongming Dongtan, Shanghai].

Ying yong sheng tai xue bao = The journal of applied ecology·2014
Same author

TRIM14 is a mitochondrial adaptor that facilitates retinoic acid-inducible gene-I-like receptor-mediated innate immune response.

Proceedings of the National Academy of Sciences of the United States of America·2014

Related Experiment Video

Updated: Jul 18, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

570

Direct training high-performance spiking neural networks for object recognition and detection.

Hong Zhang1, Yang Li1, Bin He1

  • 1State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China.

Frontiers in Neuroscience
|August 24, 2023
PubMed
Summary

This study introduces Spiking Gate (SG) ResNet and Attention Spike Decoder (ASD) for direct training of spiking neural networks (SNNs). These methods improve accuracy and overcome challenges in SNN training for object recognition and detection tasks.

Keywords:
attention spike decodergate residual learningobject detectionobject recognitionspiking RetinaNetspiking neural networks

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

795
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

9.9K

Related Experiment Videos

Last Updated: Jul 18, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

570
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

795
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

9.9K

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Spiking neural networks (SNNs) offer energy efficiency on neuromorphic hardware.
  • Direct training of SNNs is challenging due to non-differentiable spiking signals and complex dynamics.
  • Key issues include gradient vanishing/explosion, signal decoding, and upstream task applicability.

Purpose of the Study:

  • To develop effective methods for direct training of high-performance SNNs.
  • To address gradient issues and improve spiking signal decoding.
  • To enable SNNs for complex tasks like object recognition and detection.

Main Methods:

  • Introduced Spiking Gate (SG) ResNet with a binary selection gate to implement residual learning and mitigate gradient vanishing/explosion.
  • Proposed an Attention Spike Decoder (ASD) for superior spiking signal decoding compared to rate coding.
  • Integrated SG ResNet and ASD into Spiking RetinaNet for hybrid SNN-ANN object detection.

Main Results:

  • SG ResNet demonstrated superior accuracy on CIFAR-10 (94.52% top-1) and CIFAR-100 (75.64% top-1) with a minimal simulation time step.
  • Spiking RetinaNet, using SG ResNet34, achieved an mAP of 0.296 on the MSCOCO object detection dataset.
  • The proposed methods effectively overcome gradient vanishing/explosion and enhance signal decoding.

Conclusions:

  • SG ResNet and ASD are effective for direct training of SNNs, enabling high performance in object recognition.
  • The first direct-training hybrid SNN-ANN detector (Spiking RetinaNet) was developed for RGB images.
  • These advancements pave the way for more efficient and powerful SNN applications.