Brain Computer Interface project in which I use wide and deep convolutional neural networks to decode P300 component in EEG signals for a speller application. I also use saliency maps for visualizing the features learned by the model. These maps are then quantified to reveal the task-related brain dynamics.
Abstract and Poster published in Bernstein conference for computational neuroscience in Berlin in Septemper 2018.
Paper Convolutional Neural Networks for Decoding of Covert Attention Focus and Saliency Maps for EEG Feature Visualization.
For Citations.
@Article{Farahat_2019, Title = {Convolutional neural networks for decoding of covert attention focus and saliency maps for {EEG} feature visualization}, Author = {Amr Farahat and Christoph Reichert and Catherine M Sweeney-Reed and Hermann Hinrichs}, Journal = {Journal of Neural Engineering}, Year = {2019}, Month = {oct}, Number = {6}, Pages = {066010}, Volume = {16}, Doi = {10.1088/1741-2552/ab3bb4}, Publisher = {{IOP} Publishing}, Url = {https://doi.org/10.1088%2F1741-2552%2Fab3bb4} }