Artificial neural network predicts erroneous responses in the task of classifying visual stimuli
Alexander Kuc,1 Alisa Batmanova,2 Vladimir Maksimenko,1,3 1 Immanuel Kant Baltic Federal University, Kaliningrad, Russia 2 Financial University Under the Government of the Russian Federation, Moscow, Russia 3 Innopolis University, Innopolis, Russia
Abstract
In this work, we have developed an artificial neural network (ANN) trained to distinguish between
correct and erroneous behavioral reactions of the subject in the task of classifying a bistable visual
image (Necker cube). We trained ANN on EEG recordings prior to the subject's behavioral response to
the current visual stimulus. We examined the configuration of an artificial neural network, for which
the accuracy of classification of erroneous behavioral reactions exceeded 88%.
File with abstract
Speaker
Kuc Alexander
Immanuel Kant Baltic Federal University
Russia
Discussion
Ask question
