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

Neural voting machines.

Whitman Richards1, H Sebastian Seung, Galen Pickard

  • 1Computer Science and Artificial Intelligence Lab (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02139, USA. wrichards@mit.edu

Neural Networks : the Official Journal of the International Neural Network Society
|September 23, 2006
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

Uncovering Sex Differences in the Drosophila Ventral Nerve Cord Through Connectome Alignment.

bioRxiv : the preprint server for biology·2026
Same author

Eyewire II - A connectomic resource for resolving cell types and circuits of the mouse retina.

bioRxiv : the preprint server for biology·2026
Same author

Distributed control circuits across a brain-and-cord connectome.

Nature·2026
Same author

Connectomic reconstruction from hippocampal CA3 reveals spatially graded mossy fiber inputs and selective feedforward inhibition to pyramidal cells.

bioRxiv : the preprint server for biology·2025
Same author

Distributed control circuits across a brain-and-cord connectome.

bioRxiv : the preprint server for biology·2025
Same author

The synaptic architecture of layer 5 thick tufted excitatory neurons in mouse visual cortex.

Nature neuroscience·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Winner-take-all networks are suboptimal for decision-making under uncertainty. Alternative methods like Borda Count and Condorcet tally offer more robust choices, with biologically feasible network implementations proposed.

Area of Science:

  • Computational neuroscience
  • Decision-making mechanisms
  • Social choice theory

Background:

  • Winner-take-all (WTA) networks are common computational models for selecting an option based on the strongest input.
  • WTA networks perform poorly when input strengths are uncertain or when relationships between options exist.
  • Social choice theory offers alternative decision-making procedures that are more robust to uncertainty.

Purpose of the Study:

  • To explore biologically feasible neural network implementations of robust decision-making procedures.
  • To investigate alternatives to winner-take-all networks for improved information aggregation in biological systems.

Main Methods:

  • Modification of classical recurrent neural networks.
  • Development of biologically plausible network architectures.

Related Experiment Videos

  • Implementation of Social Choice procedures within neural network frameworks.

    • Main Results:

    • Proposed two novel, biologically feasible network implementations.
    • These networks are simple modifications of existing recurrent network models.
    • The implemented procedures offer more robust decision-making compared to standard WTA networks.

    Conclusions:

    • Winner-take-all networks are not always optimal for biological decision-making.
    • Alternative social choice procedures can be implemented in biologically plausible neural networks.
    • These findings suggest potential mechanisms for more sophisticated information aggregation in the brain.