Neural voting machines

Whitman Richards, Hyunjune Sebastian Seung, Galen Pickard

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


A "Winner-take-all" network is a computational mechanism for picking an alternative with the largest excitatory input. This choice is far from optimal when there is uncertainty in the strength of the inputs, and when information is available about how alternatives may be related. For some time, the Social Choice community has recognized that many other procedures will yield more robust winners. The Borda Count and the pair-wise Condorcet tally are among the most favored. If biological systems strive to optimize information aggregation, then it is of interest to examine the complexity of networks that implement these procedures. We offer two biologically feasible implementations that are relatively simple modifications of classical recurrent networks.

Original languageEnglish (US)
Pages (from-to)1161-1167
Number of pages7
JournalNeural Networks
Issue number8
StatePublished - Oct 2006

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Cognitive Neuroscience


  • Borda Count
  • Condorcet voting
  • Decision-making
  • Domain knowledge
  • Information aggregation
  • Neuroeconomics
  • Social networks
  • Winner-take-all


Dive into the research topics of 'Neural voting machines'. Together they form a unique fingerprint.

Cite this