• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

New Technology and How to Program A.I.

Status
Not open for further replies.
http://www.ted.com/talks/tan_le_a_headset_that_reads_your_brainwaves.html

I was wondering what the implication would be for scientists to use the technology that is in the above link to program artificial intelligence? I don't know how well the technology works on something like that. Reading brain waves and inputting it into an artificial intelligence seems to be one of the next logical steps in the evolution of technology.

Thanks in Advance for your Ideas.
 
I don't quite get what you're thinking here. The technology behind these devices has been in development for well over 10 years (google 'Brain Computer Interface'). Hardware records stuff from the brain, like EEG in the clip, fMRI (has much better spatial resolution than EEG, but slow changes) etc, and then feeds this (after some preprocessing) into an AI program that can guess "what the person thinks". This is still at a somewhat primitive level, it cannot really detect what you're thinking, but generally do some simple classification among a limited number of classes, say I'm thinking about moving my left hand up, or right hand down etc.

The part I don't get is how would you use EEG to "program AI", what do you even mean by it? I can't even make sense of it, not to mention that it would be the next step. I'm aware of no groups trying something like that, and I have some knowledge of this area. The data you get are not individual neurons firing or some real "brainwaves" - it's a bulk electrical activity recorded at many spots, by the time electrical signals get to the surface electrodes there's already a significant amount of interference. There have been some tests on monkeys with invasive methods, i.e. inserting electrodes into the brain, but this won't be popular except for perhaps very disabled persons. In any case, it would not make sense to try to use this data to create AI programs. You do need existing AI programs to process this data, but that's precisely what the technology is about and already does. It does not give out a new class of AI programs.
 
http://www.ted.com/talks/tan_le_a_headset_that_reads_your_brainwaves.html

I was wondering what the implication would be for scientists to use the technology that is in the above link to program artificial intelligence? I don't know how well the technology works on something like that. Reading brain waves and inputting it into an artificial intelligence seems to be one of the next logical steps in the evolution of technology.

Thanks in Advance for your Ideas.

Thank you for the TED video.

I find it very interesting and the software and the hardware are amazing.
This would mean a lot for paralyzed people. Wonderful what that lady and the researchers / technicians /programmers/developers with her have done.
Also the use of this to control robotics will be a wonderful feature.

Wonderful and amazing. I am speechless...

I do suspect that image thinkers can operate this system more easy.
But the beautiful aspect about that is that every human being is an natural image thinker. It is merely "unlearned" or forgotten by those who do not seem to be image thinkers.

About Tan Le :

http://www.emotiv.com/

I wonder how the sensors work.

It seems to measure the calcium potassium differences in the brain (electric fields moving around comprised of combined pulses )?

http://www.scientificamerican.com/article.cfm?id=brain-electric-field


They mention saline (sweat sensors ) ? I find that hard to believe ...
 
Last edited:
Status
Not open for further replies.
Back
Top