Decoding the Neural Activity of Recurrent Neural Network Playing a Reflexive Game

Описание

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: 6th Scientific School "Dynamics of Complex Networks and their Applications", DCNA 2022

Год издания: 2022

Идентификатор DOI: 10.1109/DCNA56428.2022.9923193

Ключевые слова: attractors, neural activity patterns, neural network-based decoding, reflection, reflexive games

Аннотация: We demonstrate the possibility of identification of certain stimuli time series, which is received by simple recurrent neural network while playing a reflexive game 'Even-Odd' (Matching Pennies), using its neural activity patterns. For successful identification by the method of neural network-based decoding, a non-linear decoder wiПоказать полностьюth at least 6 neurons on the hidden layer is required. This result indicates the presence of attractors of neural activity, which allow the trained recurrent neural network to determine the type of the received stimuli sequence and form the right response. © 2022 IEEE.

Ссылки на полный текст

Издание

Журнал: Proceedings - 6th Scientific School "Dynamics of Complex Networks and their Applications", DCNA 2022

Номера страниц: 185-188

Издатель: Institute of Electrical and Electronics Engineers Inc.

Персоны

  • Markova G. (Siberian Federal University, Department of Biophysics, Krasnoyarsk, Russian Federation)
  • Bartsev S. (Siberian Federal University, Department of Biophysics, Krasnoyarsk, Russian Federation, Biophysics Institute of the Siberian Branch of the Ras, Federal Research Center, Krasnoyarsk Scientific Center of the Siberian Branch of the Ras, Krasnoyarsk, Russian Federation)

Вхождение в базы данных