Decoding of stimuli time series by neural activity patterns of recurrent neural network : научное издание

Описание

Тип публикации: статья из журнала

Год издания: 2022

Идентификатор DOI: 10.1088/1742-6596/2388/1/012052

Аннотация: <jats:title>Abstract</jats:title> <jats:p>The study is concerned with question whether it is possible to identify the specific sequence of input stimuli received by artificial neural network using its neural activity pattern. We used neural activity of simple recurrent neural network in course of “Even-Odd” game simulation. For ideПоказать полностьюntification of input sequences we applied the method of neural network-based decoding. Multilayer decoding neural network is required for this task. The accuracy of decoding appears up to 80%. Based on the results: 1) residual excitation levels of recurrent network’s neurons are important for stimuli time series processing, 2) trajectories of neural activity of recurrent networks while receiving a specific input stimuli sequence are complex cycles, we claim the presence of neural activity attractors even in extremely simple neural networks. This result suggests the fundamental role of attractor dynamics in reflexive processes.</jats:p>

Ссылки на полный текст

Издание

Журнал: Journal of Physics: Conference Series

Выпуск журнала: Т. 2388, 1

Номера страниц: 012052

ISSN журнала: 17426588

Место издания: Bristol

Издатель: IOP Publishing

Вхождение в базы данных