Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Natural image reconstruction from brain waves

biorxiv.org

Post reply on HN
Print view View original

31–40 of 41 posts

Re: Natural image reconstruction from brain waves

#31

Post by buboard »

londons_explore wrote: post #30
anonytrary wrote: post #13

I'm highly skeptical. I mean, a hash function that has four output states also maps anything to one of those four states. That doesn't mean it's some next-level classifier. The problem here is EEG. EEG bandwidth is not enough to capture that much information. There is far too much noise introduced by the skull and muscles. It's most likely physically impossible to do something like this with EEG. What's likely happen…

fMRI seems to avoid many of the bandwidth issues EEG has, at least from a theoretical if not practical position. With enough receive antennas and processing power, you can get almost unbounded 3D resolution.

i wonder if one day fMRIs become a home fixture like washing machines

Re: Natural image reconstruction from brain waves

#32

Post by dr_zoidberg »

vanderZwan wrote: post #28
henearkr wrote: post #27

Earlier quoted context omitted.

Exactly. I have always been wondering how could the brain waves measurements not be overwhelmed by facial muscle signals.

If you have multiple different points where you measure, which all have this overlapping signal problems but at different strengths, couldn't you hypothetically build up a model that "solves" these different weights and untangles the signals?

Yes, but... At the end, you're still reconstructing pieces of information from something that was almost destroyed. Picture it this way: there are amazing deconvolution algorithms that can "undo" all sortf of noise and lack of focuse -- but the end result, however good to the original "bad" data isn't nearly as good as a well taken image to begin with.

Disclaimer: I work in image processing, so the example may be a bit obvious to me.

Re: Natural image reconstruction from brain waves

#33

Post by dr_dshiv »

My research group is doing the same thing but with music. Music may be more promising than images because of the Frequency Following Response -- a sort of direct resonance effect in the brain in response to sound.

We have 24 subjects listening to 12 songs in random order, with 128 channel EEG sampling at 1000hz. We can then label all these data points with the musical features at the time the data is collected.

We don't have a public repo yet, but we are sharing data.

Re: Natural image reconstruction from brain waves

#34

Post by jileczech »

unscrupulous_sw wrote: post #22

Imagine the shitshow this will cause once law enforcement adopts this. Currently eyewitness criminal sketches are still drawn by artist so they are naturally low fidelity. That will change once you can generate a photo of a face (like https://thispersondoesnotexist.com/ ) based on your brain waves. This will be disastrous on so many levels. The eyewitness might not have a good sample of a minority race. The GAN datas…

as someone in this thread pointed out, the model is overfit.

I did my thesis on EEG signals, also having a very idealistic view of what could I do with it, only to find that even the most basic of tasks is hard to classify (even to find motor cortex movement intention signatures (if you want to move left or right hand)).

This work will not go into the real world in this stage, as it is badly done and most certainly having multiple flaws in the implementation, rendering it unusable in the real world.

So, don't get too stressed out about this, if it happens, it will be about 20-30 years from now. And keeping in mind how slow the law enforcement technology moves forward (aren't most of them still using windows xp and vista?) I would count more like 30-50 years.

Re: Natural image reconstruction from brain waves

#35

Post by vanderZwan »

dr_zoidberg wrote: post #32
vanderZwan wrote: post #28

Earlier quoted context omitted.

If you have multiple different points where you measure, which all have this overlapping signal problems but at different strengths, couldn't you hypothetically build up a model that "solves" these different weights and untangles the signals?

Yes, but... At the end, you're still reconstructing pieces of information from something that was almost destroyed. Picture it this way: there are amazing deconvolution algorithms that can "undo" all sortf of noise and lack of focuse -- but the end result, however good to the original "bad" data isn't nearly as good as a well taken image to begin with. Disclaimer: I work in image processing, so the example may be a b…

Isn't what I described more like reconstructing a picture from many copies that were each destroyed in a unique fashion?

Re: Natural image reconstruction from brain waves

#36

Post by _f9cu »

d-d wrote: post #2

What would a world look like where all thoughts are public?

What would a world look like where all thoughts are public.

When all thoughts a public has is a good thought.

It would be a beautiful world.

So whats the first thing any innovation should bring upon us? being good, thinking good.

What would a world look like if all innovations does good to public?

People's thought become good.

Re: Natural image reconstruction from brain waves

#37

Post by dr_zoidberg »

vanderZwan wrote: post #35
dr_zoidberg wrote: post #32

Earlier quoted context omitted.

Yes, but... At the end, you're still reconstructing pieces of information from something that was almost destroyed. Picture it this way: there are amazing deconvolution algorithms that can "undo" all sortf of noise and lack of focuse -- but the end result, however good to the original "bad" data isn't nearly as good as a well taken image to begin with. Disclaimer: I work in image processing, so the example may be a b…

Isn't what I described more like reconstructing a picture from many copies that were each destroyed in a unique fashion?

Yes, that'd be a better analogy. My point was that, even if you had the best reconstruction in the world, having to reconstruct from a degraded source is worse than working from a good source to begin with.

Re: Natural image reconstruction from brain waves

#39

Post by close04 »

dr_zoidberg wrote: post #37
vanderZwan wrote: post #35

Earlier quoted context omitted.

Isn't what I described more like reconstructing a picture from many copies that were each destroyed in a unique fashion?

Yes, that'd be a better analogy. My point was that, even if you had the best reconstruction in the world, having to reconstruct from a degraded source is worse than working from a good source to begin with.

From a practical perspective they don’t have to be perfect or as food as the original, not even close, just good enough. “Good enough” though is also extremely hard to achieve, assuming it’s even possible with this technique.

Re: Natural image reconstruction from brain waves

#40

Post by Roark66 »

I read in some article some time about use of SQUIDs (https://en.wikipedia.org/wiki/SQUID) to map activity of a single neuron non-invasively. There was a lot of hype at the time for brain-computer interfaces based on that, but then same as with many technologies that were "just 5 years away" those 5 years came and went with no deliverables expected.
Post reply on HN