Reading minds with deep learning
blog.floydhub.com
Reading minds with deep learning
1–10 of 27 posts
Re: Reading minds with deep learning
#2I think BCIs are super exciting. Humans have such high bandwidth in terms of input; tons of information is interpreted by our nervous system every second. Yet in terms of output, we are relatively poor; we can only type a few words a minute! This article suggests we could one day work 'like digital octopuses' but I'm naturally dubious, do you think it's possible as CTRL-labs propose that we could entirely rewire our nervous systems' output to let us operate computers as if we had multiple hands?
Re: Reading minds with deep learning
#3I think BCIs are super exciting. Humans have such high bandwidth in terms of input; tons of information is interpreted by our nervous system every second. Yet in terms of output, we are relatively poor; we can only type a few words a minute! This article suggests we could one day work 'like digital octopuses' but I'm naturally dubious, do you think it's possible as CTRL-labs propose that we could entirely rewire our…
Great points. Thomas reardon (CTRL-labs founder) says the same in a talk you can see on YouTube (definitely check it out). I share your doubts, and wonder exactly how neuroplastic we are. Perhaps we are simply built to operate in a certain way, and solely tapping in to our nerves responsible for output won't necessarily allow us to output in hugely different ways. Even if possible, it may not be so simple,and instead becoming a digital octopus may be like having to learn the piano, requiring years of practice!
Re: Reading minds with deep learning
#4While the results are really cool, they're not perfect, and seemingly even the best companies working with deep learning are still not getting it right every time. It makes me wonder if this technology will ever be useful for these tasks... I mean would you be willing to use BCIs even if they made small errors from time to time?
Re: Reading minds with deep learning
#5Curious about differences in brain waves for desire versus intent. I might desire to say something awful to that person who just honked at me, but I probably shouldn’t - and right now wouldn’t. Would a BCI system be able to tell the difference?
Re: Reading minds with deep learning
#6Curious about differences in brain waves for desire versus intent. I might desire to say something awful to that person who just honked at me, but I probably shouldn’t - and right now wouldn’t. Would a BCI system be able to tell the difference?
Haha, that's a fantastic point! And in order to get anywhere closer to making such differentiations, surface EEG S (used for the results into his article) would surely not suffice. The technology and results we are collecting currently are just scratching the surface, though I'd suspect if a BCI was capable of detecting intent of such complexity as the situation you described, it would also probably have the capacity to know whether it was something you planned to act on or not.
Re: Reading minds with deep learning
#7While the results are really cool, they're not perfect, and seemingly even the best companies working with deep learning are still not getting it right every time. It makes me wonder if this technology will ever be useful for these tasks... I mean would you be willing to use BCIs even if they made small errors from time to time?
Yes that's the big question, and I mention that in the article. Let's say for a moment that we can't achieve 100% accuracy, well one parallel to this situation would be autocorrect on our phones; it often corrects you when you didn't want it to or misinterprets your meaning. Yet we still use it as there is net gain in terms of convenience. If a BCI could instantly put your thought on to paper, and left you solely with a few typos to mop up, I think we'd all be willing to compromise.
Re: Reading minds with deep learning
#8While the results are really cool, they're not perfect, and seemingly even the best companies working with deep learning are still not getting it right every time. It makes me wonder if this technology will ever be useful for these tasks... I mean would you be willing to use BCIs even if they made small errors from time to time?
There is a lot of variance in error rate in biological human nerves as well. Certainly a lot of people on the low-end of the bell curve could benefit.
Interesting to consider whether a 'filter' could be made for people with parkinson's that would drop tremor noise while preserving intentional actions. Perhaps with robotic exosleeves tremor could be offset/counteracted - or eventually we could input the filtered signal back into the nerve.
Re: Reading minds with deep learning
#9If you connect a computer to a brain which element is the more sophisticated processing device?
The brain.
If you want high-fidelity cheap BCI don't bother with fancy sensors, galvanic skin response is enough. The trick is to use the high-powered processor to do the heavy lifting. You use hypnosis and create a simple feedback loop to calibrate e.g. one channel per finger and one per thumb. That gives you 8 data lines and a clock/ack signal. An eight-bit parallel port from your mind to your computer. You can now come out of trance and "type" by thinking at the machine in a certain way (no imaginary keyboard) and your verbal thoughts appear on the screen. Other output modalities are possible. It's fucking trivial, if you'll pardon my language.
It's ridiculous to connect a computer to a brain and then concentrate on the computer, rather than the brain, to develop control and communication systems. It's a bit like trying to move your bicycle using a skateboard.
But the greater problem with focusing on the CPU rather than the brain is that it reinforces a world that doesn't demand much personal growth to use powerful tools. BCI where the computer does the work relieves the user of learning how to operate his or her own brain. BCI-by-hypnosis requires the user to learn enough self-operation to be able to go into a light trance and learn a simple motor pattern, and the meta-lesson "side effect" is more valuable and more important than the ability to interact with computers with greater facility.
(BTW, I doubt this would ever be a mass-market product, because you're not just selling a peripheral at that point...)
- - - -
edit: Folks, I'm gonna ask that you please not downvote me on this one without saying something about why. I've never been able to get anyone to listen or take me seriously on this particular subject, and frankly that sucks. I know this works but no one cares and it's frustrating. So, again, please, if you think this is worth a downvote can you please take a minute and tell me why?
Re: Reading minds with deep learning
#10I think BCIs are super exciting. Humans have such high bandwidth in terms of input; tons of information is interpreted by our nervous system every second. Yet in terms of output, we are relatively poor; we can only type a few words a minute! This article suggests we could one day work 'like digital octopuses' but I'm naturally dubious, do you think it's possible as CTRL-labs propose that we could entirely rewire our…
Great points. Thomas reardon (CTRL-labs founder) says the same in a talk you can see on YouTube (definitely check it out). I share your doubts, and wonder exactly how neuroplastic we are. Perhaps we are simply built to operate in a certain way, and solely tapping in to our nerves responsible for output won't necessarily allow us to output in hugely different ways. Even if possible, it may not be so simple,and instead…
Here's that talk you mentioned:
https://www.youtube.com/watch?v=5Z5aZK2C3ew (2018 O'Reilly AI Keynote, Thomas Reardon, CEO, CTRL-labs)