[yoz-y]

I worked in non invasive BCIs for a couple of years (this was about 7 years ago). My current horizon estimation for a “put a helmet and gave usable brain computer interface” is never.

With implants, we are probably decades away.

What currently works best is monitoring the motor cortex with implants as those signals are relatively simple to decode (and from what I recall we start to be able to get pretty fine control). Anything tied to higher level thought is far away.

As for thought itself, I wonder how would we go about it (assuming we manage to decode it). It’s akin to making a voice controller interface, except you have to tell aloud everything you are thinking.

[mkaic]

Have you kept up with recent ML papers like MindEye, which have managed to reconstruct seen images using image generator models conditioned on fMRI signals?

Ever since that paper came out, I (someone who works in ML but have no neuroimaging expertise) have been really excited for the future of noninvasive BCU.

Would also be curious to know if you have any thoughts on the several start-ups working in parallel on optimally pumped magnetometers for portable MEG helmets.

[yoz-y]

> Have you kept up with recent ML papers like MindEye, which have managed to reconstruct seen images using image generator models conditioned on fMRI signals?

Not really. I left the field mostly because I felt bitter. I find that most papers in the field are more engineering than research. I skimmed through the MindEye paper and don’t find it very interesting. It’s more of mapping of “people looking at images in a fMRI” to identifying the shown image. They make the leap of saying that this is usable to detect actual mind’s eye (they cite a paper where they requires 40 hours of per-subject training, on the specific dataset) which I quite doubt. Also we’re nowhere near having a portable fMRI.

As for portable MEG, assuming they can do it: it would be indeed interesting. Since it still relies on synchronized regions I don’t think high level thinking detection is possible but it could be better for detecting motor activity and some mental states.