Brain–computer interfaces (BCIs) decipher and translate brain signals
into commands for the surrounding environment. Different types of brain
signals, e.g., EEG and fMRI, have been used as a means to decode
intended user commands, and various machine learning approaches have
been tested in such a task. With the advent of the deep learning (DL)
era, new studies have emerged that exploit the advantages of the deep
network architectures for BCI systems and depict more efficient and
reliable brain signal decoding systems.
The aim of this Special Issue
is to provide a collection of forefront works investigating the
deployment of various deep network types in different BCI applications
using a variety of brain signals either of unimodal or multimodal signal
processing framework. Topics of interest include but are not limited to
the following: