Datasets for Reconstructing Visual Perception from Brain Data
github.com41 points by katsee 7 hours ago
41 points by katsee 7 hours ago
There was this research where faces were almost perfectly reconstructed from money's brain signals. How were they able to achieve such perfect recreation from monkey but not even close from human brain.
Is there a case for non-dystopian applications for such a project, should it succeed?
I get that we're all driven by curiosity, and the brain is very mysterious, but at some point I really wonder when scientists will start to taboo projects like this for ethical reasons, just like they currently taboo human cloning.
I dont know anything about neurosience But if dreaming is related enouth to visual perception, maybe a dream recorder might be somewhat possible
Edit, reading the github description, which i should have done sooner, hints at dreams.
Every researcher working on this should be required to watch Until the End of the World.
Reconstruction of inner experience - imagery, maybe dreams & hallucinations, perceptual phenomena.
Here is a recent study reconstructing the inner perception of optical illusions: https://www.science.org/doi/abs/10.1126/sciadv.adj3906
Methods like MVPA (decoding among finite sets of cognitive state classes) are actually widely used for insight in cognitive neuroscience.
Ethical concerns are discussed within the field; most papers had explicit ethics sections and discussions long before AI conferences required them for all submissions. In practice these experiments require a participant lying motionless (≈1-2 mm range) in an MRI scanner with controlled gaze and attention for many hours, and even then zero-shot reconstruction is not really possible; the SNR requires many repetitions.
Dystopian applications are extremely impractical or impossible, this is a tool for neuroscience