Recurrent and multi-layer neural networks playing "Even-Odd": reflection against regression
URI (для ссылок/цитирований):
https://iopscience.iop.org/article/10.1088/1757-899X/734/1/012109https://elib.sfu-kras.ru/handle/2311/142340
Автор:
Барцев, Сергей Игоревич
Маркова, Галия Муратовна
Коллективный автор:
Институт фундаментальной биологии и биотехнологии
Кафедра биофизики
Дата:
2020-01Журнал:
IOP Conference Series: Materials Science and EngineeringКвартиль журнала в Scopus:
без квартиляКвартиль журнала в Web of Science:
без квартиляБиблиографическое описание:
Барцев, Сергей Игоревич. Recurrent and multi-layer neural networks playing "Even-Odd": reflection against regression [Текст] / Сергей Игоревич Барцев, Галия Муратовна Маркова // IOP Conference Series: Materials Science and Engineering. — 2020. — Т. 734.Аннотация:
Reflection understood as an internal representation of the external world by the
subject is the key property of consciousness. In a refined form this property is manifested in
reflective games. To win a reflective game a player has to use reflection of strictly one rank
higher than the opponent. So it can be assumed that there are only two game modes - when
only one player uses reflection and wins and when both players use reflection but one of them
chooses incorrect reflection rank. The option of random move selection is not considered since
firstly, starting the game for a draw is strange, and secondly, it is technically impossible to
make random moves without a special device. Experiments with recurrent neural networks
playing with each other showed that the entire set of game patterns (time series of the game
score) is split into two sharply different groups that can be associated with two modes
mentioned above. Experiments, in which a multilayer neural network, which is basically
incapable of reflection, played against a recurrent neural network, showed that a recurrent
neural network has a clear advantage winning confidently in more than 90% of the games. At
the same time game patterns demonstrate splitting into two sharply different groups as was
observed in experiments with the game of two recurrent neural networks and in the reflexive
game of living people.