Remember this is over a year old and only what's public based on limited datasets...
One commenter suggested "if you got good sensitive sensors and like 10,000 people, +10,000 video clips, then you could make a good large general dataset. Training on that would give a great result."
Another relayed a thought I've had "Would love to watch my dreams from the night before."
"As part of the NeuroNet NTI Assistive Neurotechnology project, employees of the Neurobotics Group of Companies and the Moscow Institute of Physics and Technology have trained neural networks to recreate images of the electrical activity of the brain. Earlier, no such experiments were performed on EEG material (other scientists used fMRI or analyzed signals directly from neurons). In the future, this discovery will create a new type of device for post-stroke rehabilitation."