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

Unsupervised learning of visual features through spike timing dependent plasticity.

Timothée Masquelier1, Simon J Thorpe

  • 1Centre de Recherche Cerveau et Cognition, Centre National de la Recherche Scientifique, Université Paul Sabatier, Faculté de Médecine de Rangueil, Toulouse, France. timothee.masquelier@alum.mit.edu

Plos Computational Biology
|February 20, 2007
PubMed
Summary

Spike-timing dependent plasticity (STDP) in neural networks helps recognize visual features. This learning rule enables fast and selective responses, mimicking the brain's visual processing speed.

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

Towards a better understanding of real-life hearing impairments via electrophysiology.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Temporal recurrence as a general mechanism to explain neural responses in the auditory system.

Communications biology·2025
Same author

A general model unifying the adaptive, transient and sustained properties of ON and OFF auditory neural responses.

PLoS computational biology·2024
Same author

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence.

Science advances·2023
Same author

Brain-guided manifold transferring to improve the performance of spiking neural networks in image classification.

Journal of computational neuroscience·2023
Same author

Optical flow estimation from event-based cameras and spiking neural networks.

Frontiers in neuroscience·2023

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Spike-timing dependent plasticity (STDP) modifies synaptic strength based on pre- and post-synaptic spike timing.
  • Repeated similar inputs to neurons concentrate synaptic weights on early-firing afferents, decreasing postsynaptic spike latencies.

Purpose of the Study:

  • To investigate the emergence of visual feature selectivity in a spiking neural network using STDP.
  • To demonstrate how STDP can lead to robust object recognition and fast, selective responses.

Main Methods:

  • Utilized an asynchronous feedforward spiking neural network model.
  • Employed STDP as the learning rule.
  • Trained the network on natural images to identify emergent feature selectivity.

Main Results:

Related Experiment Videos

  • The network developed selectivity to intermediate-complexity visual features.
  • These features represent salient and consistently present patterns in natural images.
  • The learned features enabled robust object recognition across various classification tasks.

Conclusions:

  • Temporal codes are crucial for understanding the visual system's processing speed.
  • STDP is a viable mechanism for achieving fast and selective neural responses.
  • This model highlights STDP's role in efficient visual information processing.