Voting procedures from the perspective of theory of neural networks

Abstract

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.

Foresight technology in the integration of education, science and production

“…As a result of the research, a software system was developed that is designed to automate the data processing process. The system allows for data mining, retrieving missing data, increasing the processing speed and convenience of presenting data to the end-user in comparison with classical methods [15].…”

Artificial Intelligence In The Context Of Noosphere Studies

“…Namely, any use value of any product has two components. One of them is directly related to its functional purpose, and the other one is responsible for using the product to demonstrate the status of the owner (as cited in Suleimenov, Panchenko, & Gabrielyan, 2016).…”

Complex systems’ self-organization theory: Bureaucracy

“…Авторы считают, что в данной работе новыми являются следующие положения и результаты: простейшим примером системы, существующей на практике и проявляющей нейросетевые свойства, является голосующий совет [5]. В идеализированном случае каждому члену некоторого совета, принимающего решение методом голосования (например, диссертационного совета) можно поставить в соответствие аналог нейрона.…”