TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Natural image reconstruction from brain waves

117 pointsby soofyover 5 years ago

11 comments

anonytraryover 5 years ago
I&#x27;m highly skeptical. I mean, a hash function that has four output states also maps <i>anything</i> to one of those four states. That doesn&#x27;t mean it&#x27;s some next-level classifier.<p>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&#x27;s most likely physically impossible to do something like this with EEG.<p>What&#x27;s likely happening here is that there&#x27;s some large scale oscillations that are sufficiently unique to discern the images from each other. This does not mean they are reproducing the images. I am highly skeptical of the methods used here -- they are almost certainly flawed.<p>I, too, once had dreams of conquering the planet with EEG when I was a grad student. I quickly learned that physics makes this infeasible. Anyone who is serious about BMIs are studying invasive BMIs and how to make them as safe as possible. Going inside the brain is unavoidable, I&#x27;m afraid.
评论 #21450540 未加载
评论 #21450714 未加载
评论 #21450429 未加载
评论 #21451388 未加载
echelonover 5 years ago
This model is incredibly overfit.<p>Video: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;nf-P3b2AnZw" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;nf-P3b2AnZw</a><p>Watch how it has preconceived notions of these scenes. It frequently fails to reconstruct the correct scene from video, and it also turns completely blank input into one of the scenes it was trained on.
unscrupulous_swover 5 years ago
Imagine the shitshow this will cause once law enforcement adopts this.<p>Currently eyewitness criminal sketches are still drawn by artist so they are naturally low fidelity.<p>That will change once you can generate a photo of a face (like <a href="https:&#x2F;&#x2F;thispersondoesnotexist.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;thispersondoesnotexist.com&#x2F;</a>) based on your brain waves.<p>This will be disastrous on so many levels. The eyewitness might not have a good sample of a minority race. The GAN dataset itself might also only be trained on celebrity faces so it doesn&#x27;t know how to generate anything else (e.g., a teen).<p>But it will be deceptively high resolution so police will rely on it.<p>If you have a generic face your life is fucked.
评论 #21450788 未加载
评论 #21451614 未加载
评论 #21451376 未加载
dr_dshivover 5 years ago
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.<p>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.<p>We don&#x27;t have a public repo yet, but we are sharing data.
lbjover 5 years ago
I dont think their model is working, and Im not sure it ever will. Simply reading brainwaves, a bi-product as I understand it, of the actual neuron activity, couldn&#x27;t possibly give you an accurate result.
rangibabyover 5 years ago
The end results are much, much better than I thought they would be. Luckily, I think it would be easy to fool the training by thinking about a totally different image to the baseline one. Idk if that would stand up to rubber hose cryptanalysis, but there’s got to be a way that can.
评论 #21450427 未加载
Roark66over 5 years ago
I read in some article some time about use of SQUIDs (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;SQUID" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;SQUID</a>) 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 &quot;just 5 years away&quot; those 5 years came and went with no deliverables expected.
snowwrestlerover 5 years ago
There’s a great movie called <i>Until The End Of The World</i> that centers on this kind of technology. Once the scientists get it to work, they realize that they can record and play back their dreams, and they become addicted to watching them.
raszover 5 years ago
Lena source image resulting in some other random woman &quot;reconstruction&quot; = model over fitted AF. Put a dead fist and it will continue generating &quot;reconstructions&quot;.
olliejover 5 years ago
It’s interesting to see that the reconstructed Lenna has the high quality reconstruction, but of a generic woman.
评论 #21450199 未加载
d-dover 5 years ago
What would a world look like where all thoughts are public?
评论 #21450163 未加载
评论 #21450213 未加载
评论 #21450271 未加载
评论 #21450437 未加载
评论 #21451899 未加载
评论 #21451025 未加载
评论 #21450131 未加载