Voting procedures from the perspective of theory of neural networks
It is shown that voting procedure in any authority can be treated as Hopfield neural network analogue. It was revealed that weight coefficients of neural network which has discrete outputs −1 and 1 can be replaced by coefficients of a discrete set (−1, 0, 1). This gives us the opportunity to qualita...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2016-11-01
|
| Series: | Open Engineering |
| Subjects: | |
| Online Access: | http://www.degruyter.com/view/j/eng.2016.6.issue-1/eng-2016-0048/eng-2016-0048.xml?format=INT |
| Summary: | It is shown that voting procedure in any authority
can be treated as Hopfield neural network analogue.
It was revealed that weight coefficients of neural network
which has discrete outputs −1 and 1 can be replaced by coefficients
of a discrete set (−1, 0, 1). This gives us the opportunity
to qualitatively analyze the voting procedure on the
basis of limited data about mutual influence of members. It
also proves that result of voting procedure is actually taken
by network formed by voting members. |
|---|---|
| ISSN: | 2391-5439 |