Use of artificial intelligence for study of the visual perception

In this report we propose an approach based on artificial neural networks for the classification and recognition of various states of the human brain associated with the spatial perception of ambiguous images. Based on the developed numerical methodology and analysis of the experimental multi-channel EEG data, we create and optimize an artificial neural network to ensure the accuracy of the classification of EEG states of the brain in visual perception close to 100%. Different interpretations of ambiguous images produce di ff erent oscillatory patterns in the EEG of a person with similar characteristics for each interpretation.