Neural Network

[CajunCenturion]

http://www.napa.ufl.edu/2004news/braindish.htm

 

[CajunCenturion]

Sorry about the link:

Neural Network

Good Luck
--------------
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[MasterRacker]

Cool. It will be interesting to see what comes out of that.


Jeff
The future is already here - it's just not widely distributed yet...

 

[ecobb]

All stealth bombers are upgraded with neural processors, becoming fully unmanned. One of them, Skynet, begins to learn at a geometric rate. It becomes self-aware at 2:14 a.m. eastern time, August 29.

http://sssup1.sssup.it/~giorgio/movies/ac-eng.html

I had to do it!!




Hope This Helps!

Ecobb
Beer Consumption Analyst

"My work is a game, a very serious game." - M.C. Escher

 

[chiph]

Thank you for flying with Petri Dish Airlines, I'm your pilot for our flight today, Pinkie. Narfff!"

Chip H.


____________________________________________________________________
If you want to get the best response to a question, please read FAQ222-2244 first

 

[harebrain]

Gee, if you called it "Rat Airlines," then you'd have a variation of the old joke regarding the merger of Chinese Air Transport" (CAT) and Scandinavian Air Service (?) (SAS). Too bad the study didn't come from somewhere in Scandinavia!

 

[Onyxpurr]

How surreal...Thanks for sharing.

 

[sleipnir214]

This sounds to me like science catching up to science fiction. The concept of biological control components crops up quite often.


Want the best answers? Ask the best questions!

TANSTAAFL!!

 

[hotfusion]

I can't help feeling that the whole story was exaggerated somewhat; The writer appears to be more than 'just a journalist', although I fail to see how a bunch of interconnected rat's brain cells can fly a simulator, to any degree. After all, the 'brain' would have to learn what was actually required before it could pilot the plane in level flight. I know they referred to a feedback loop, but again, how does the brain accept a certain stimulus as meaning the equivalent of 'wrong'?

The idea of flying a plane correctly is a purely human one, and that only because we have been taught the consequences of getting it wrong.
I don't honestly think a dish of rat brain would have the ability to deduce that, and in any case would have no desire to do so, even if it could decide. It matters not to the 'sub-brain' whether it maintains an electrode at a given potential or not, as it suffers no ill effects for not doing so.

That aside, I do understand that wasn't really supposed to be the point of the experiment anyhow, and I feel experiments in this direction could ultimately leed to some seriously interesting discoveries.

I just wish the writers would keep sensationalist scripts to themselves, and concentrate more on fact......

Regards, Andy.
**************************************
My pathetic attempts at learning HTML can be laughed at here:

http://myweb.tiscali.co.uk/andyspatch/index.htm

 

[GwydionM]

Flies fly, and so do gnats. A sub-intelligent machine that can fly itself is perfectly possibly, and nothing new. 'Neural networks' have been around for years.

Science fiction has in fact trailed behind reality. The easiest way to think about a computer or robot is to make them just like a person, with the same mode of thinking. But as programmers, we know that computers work in an utterly different manner and that it takes a lot of cleverness to hide their alien nature. I doubt neural nets will be any different.

A neural net with as many connections as a rat-brain might possibly be as clever as a rat, and no cleverer. We might be able to get it to do interesting tasks for us, but that's all it would do.

There's also the interesting fact that as pre-humans got cleverer, the process of learning and childhood got a lot longer. Compaire a 4-year-old human with a 4-year-old horse, say. Natural selection would not have favoured a very long and unproductive childhood unless this were absolutely necessary for the maturing of a human-sized brain.

------------------------------
A view from the UK

 

[kmfna]

I don't know...could it really be as clever as any living organism (barring plant life and Steven Hawking, of course)?? Since living organisms have certain inherited instincts, born of generations of growth, trial and experience, I find it hard to imagine that some random cells could show any real level of capability...but hey, I'm not a scientist, so who knows???

Kevin

- "The truth hurts, maybe not as much as jumping on a bicycle with no seat, but it hurts.

 

[hotfusion]

Despite what I consider to be 'over-reporting' in this case, the whole idea of the development of a biological computer is a fascinating subject and just might be something we have to get used to in the distant future. As indicated by GwydionM, the brain as we know it takes a long time to 'program', but that is only because it learns by experience, which is bound to take time. It might be possible, however, to be able to dump data directly into a freshly grown 'virgin' brain, much as one might image a hard drive......

Computing using binary code and semiconductors seems to have found itself wanting when it comes to attempting to create intelligence, but if some other - perhaps as yet un-thought of - technology comes to the fore, maybe we will see the emergence of a truly intelligent machine?

Regards, Andy.
**************************************
My pathetic attempts at learning HTML can be laughed at here:

http://myweb.tiscali.co.uk/andyspatch/index.htm