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

Hebbian learning in parallel and modular memories

C S Poon1, J V Shah

  • 1Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge 02139, USA. cpoon@cybernet.mit.edu

Biological Cybernetics
|April 3, 1998
PubMed
Summary
This summary is machine-generated.

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

Evaluation of cranial capacity by mustard seed technique.

Journal of the Indian Medical Association·2013
Same author

Impact of Construction Waste Disposal Charging Scheme on work practices at construction sites in Hong Kong.

Waste management (New York, N.Y.)·2012
Same author

Environmental management system vs green specifications: how do they complement each other in the construction industry?

Journal of environmental management·2010
Same author

Factors affecting the implementation of green specifications in construction.

Journal of environmental management·2009
Same author

Cultural shift towards sustainability in the construction industry of Hong Kong.

Journal of environmental management·2009
Same author

Influences of chemical activators on incinerator bottom ash.

Waste management (New York, N.Y.)·2008
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

Hebbian learning in parallel brain memory systems is more efficient and simpler than backpropagation. This research proposes a biologically relevant tree-like perceptron model for neural networks.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Brain functions rely on parallel and modular memory subsystems.
  • Hebbian synaptic plasticity adapts these subsystems.
  • Supervised learning models like multilayer perceptrons use backpropagation, differing from biological systems.

Purpose of the Study:

  • To demonstrate the advantages of Hebbian learning in parallel/modular memories over backpropagation in lumped memories.
  • To propose a more biologically relevant neural network model.

Main Methods:

  • Comparison of Hebbian learning in parallel/modular systems versus backpropagation in lumped systems.
  • Development of a modified multilayer perceptron model (tree-like perceptron).
  • Modeling neuronal specificity and synaptic plasticity rules.

Related Experiment Videos

Main Results:

  • Hebbian learning is computationally more efficient and structurally simpler for biological implementation.
  • The tree-like perceptron model incorporates parallel/modular architecture and specific synaptic plasticity rules.
  • This model aligns with neocortical and cerebellar system architectures.

Conclusions:

  • Parallel and modular memory systems with Hebbian plasticity offer significant advantages over traditional backpropagation models.
  • The proposed tree-like perceptron provides a more biologically plausible framework for understanding brain function and developing neural networks.