Neural Voting Machines
ÂWinner-take-all networks typically pick as winners that 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. In the Social Choice community,...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30513 |
| _version_ | 1826194801943379968 |
|---|---|
| author | Richards, Whitman Seung, H. Sebastian |
| author_facet | Richards, Whitman Seung, H. Sebastian |
| author_sort | Richards, Whitman |
| collection | MIT |
| description | ÂWinner-take-all networks typically pick as winners that 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. In the Social Choice community, many other procedures will yield more robust winners. The Borda Count and the pair-wise Condorcet tally are among the most favored. Their implementations are simple modifications of classical recurrent networks. |
| first_indexed | 2024-09-23T10:02:01Z |
| id | mit-1721.1/30513 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:02:01Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/305132019-04-12T08:37:37Z Neural Voting Machines Richards, Whitman Seung, H. Sebastian AI WTA Borda machine Condorcet procedure neural network ÂWinner-take-all networks typically pick as winners that 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. In the Social Choice community, many other procedures will yield more robust winners. The Borda Count and the pair-wise Condorcet tally are among the most favored. Their implementations are simple modifications of classical recurrent networks. 2005-12-22T02:20:05Z 2005-12-22T02:20:05Z 2004-12-31 MIT-CSAIL-TR-2004-083 AIM-2004-029 http://hdl.handle.net/1721.1/30513 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 12 p. 13714512 bytes 523751 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI WTA Borda machine Condorcet procedure neural network Richards, Whitman Seung, H. Sebastian Neural Voting Machines |
| title | Neural Voting Machines |
| title_full | Neural Voting Machines |
| title_fullStr | Neural Voting Machines |
| title_full_unstemmed | Neural Voting Machines |
| title_short | Neural Voting Machines |
| title_sort | neural voting machines |
| topic | AI WTA Borda machine Condorcet procedure neural network |
| url | http://hdl.handle.net/1721.1/30513 |
| work_keys_str_mv | AT richardswhitman neuralvotingmachines AT seunghsebastian neuralvotingmachines |