Enter your username and password.
-
posts about #neurogrid more →
How Much Power Does It Take To Simulate The Human Brain?
| posts about #neurogrid more → |
How Much Power Does It Take To Simulate The Human Brain? |
11/09/09
Traditional training algorithms like Back Propagation start to really grind as the network and pattern space grow and other modified approaches don't do that much better. I don't hear Boahen addressing this.
Building more neurons that lack the required organization and learning algorithms is like putting a human brain in a blender, turning it on for a few seconds and then declaring that the jug has the processing power of Albert Einstein!
DARPA has been sinking money in to this kind of work for decades with very little to show for it (although not as much as they've wasted on "traditional" AI). A lot of the groups that continue to receive funding make extremely bold claims, but they can't substantiate any of them (a certain group at MIT springs to mind).
In case you think I'm just talking out of my rear, I say all this having worked on a DARPA Neuromorphic Computing project until a couple of years ago. I also originally started my Ph.D. in the implementation of neurons on silicon chips before switching to another subject.
Of course this kind of work is important and should be funded because one decade a may lead to something. However, it should be able to exist and to have academic freedom (and funding) without having to make outrageous claims. #neurogrid
11/09/09
Then you have to listen to it tell bad jokes for a few years. #neurogrid
11/09/09
11/09/09
In the meantime, we have a lot of background processes that our brains control. These things range from controlling our heartbeat to managing our hormone load for any given purpose like arousal or mood, down to our excretory systems and not letting us crap ourselves while sleeping.
Add to this the management of movement and interpretation of touch and other stimulus that a robot couldn't even hope to manage at the present time. Include in this the ability to process and interpret visual stimulus, which means filtering out background noise, flipping the upside down image that comes through our eyes, and then interpreting an orange as ripe, not ripe, food or not food, something to be eaten or saved for later.
Your brain is doing so many things at once that you're not even remotely cognizant of that it's silly. Compare yourself as a walking, talking, remembering, feeling and gizmodo reading being to an unfortunate person who's now braindead on life support in the hospital; with the right help their body can live, but it can not interact in any way whatsoever, and for all practical purposes won't even respond except locally through redness, etc. to painful stimulus.
At the moment at least, even the best supercomputers are basically no more aware than a starfish, with its decentralized neural net. When instructed by its hormones to feel hunger, it will search out food until one of its arms finds something its sensory apparatus has been instinctually instructed to recognize as tasty, and then it will fulfill its instinctual coding to solve the problem of hunting and eating this food. Then it'll move on and patiently wait until the next set of hormonal instructions need to be fulfilled. It, like a computer has no hopes and dreams, or plans for the afternoon. #neurogrid
11/10/09
11/09/09
11/09/09
11/09/09
11/09/09
11/09/09
11/09/09
I suddenly now have a new excuse for EVERYTHING! #neurogrid
11/09/09
11/09/09
Kwabena Boahen, a computer scientist at Stanford University, believes that it would require 10 megawatts to power a processor as smart as the human brain. His new "Neurogrid" supercomputer might be able to do it on only 20 watts. #neurogrid
11/09/09
11/09/09
11/09/09
@Erix_Cale: I prefer The Foreigner!
"I'm not from here! I have my own customs! Look at my craaaaaazy passport!" #neurogrid
11/09/09
11/09/09
11/09/09