Slashdot Mirror
Silicon Brains That Think As Fast As a Fly Can Smell
Nerval's Lobster writes "Researchers in Germany have discovered what they say is a way to get computers to do more than execute all the steps of a problem-solving calculation as fast as possible – by getting them to imitate the human brain's habit of finding shortcuts to the right answer. A team of scientists from Freie Universität Berlin, the Bernstein Center Berlin, and Heidelberg University have refined the idea of parallel computing into one they describe as neuromorphic computing. In their design, a whole series of processors designed as silicon neurons rather than ordinary CPUs are linked together in a network similar to the highly interconnected mesh that links nerve cells in the human brain. Problems fed into the neuro mesh are broken up and processed in parallel, but not always using the same process. The method by which neuromorphic processors handle problems varies with the way they're linked together, as is the case with neurons in the brain. The chips are designed to copy the layout and functions of brain cells, but the way they're interconnected is based on another highly efficient biological model. 'The design of the network architecture has been inspired by the odor-processing nervous system of insects,' said one of the researchers. 'This system is optimized by nature for a highly parallel processing of the complex chemical world.' In tests using real-world datasets, the prototype was able to match the performance of specialized Bayeseian pattern-matching systems. Even better, the stable decisions reached by 'output neuron populations' take approximately 100 milliseconds, which is the same speed required by the insect nervous systems on which the network design is based, according to the paper."
In order to properly evaluate this story I would need to know the rate at which flies smell. although presumably silicon ICs can move faster than that.
Is that fast enough to make the Kessel Run in less than twelve parsecs?
I can't wait to see what this does to the automated market robots.
...I read it as: Silicon Breasts That can Think...
Guess that means that mine can't think as fast as my house banana flies can smell.
What this world is coming to - is for you and me to decide.
... isn't a parsec a unit of distance, not time?
Priest: "Universe from nothing, no laws of physics, sped up time"+ huge discrepancies. Creationism? No. Big Bang Theory
That's the last thing we need: robot overlords who keep taking shortcuts. Next thing you know, they'll kill all humans and then go bankrupt from ill-advised mortgages!
The method by which neuromorphic processors handle problems varies with the way they're linked together, as is the case with neurons in the brain.
First of all, no one knows how neurons are linked together in the brain(*).
Second of all, as far as anyone can tell, the cerebral cortex is a repeated pattern of small structures ("Cortical Columns") which are, again - as far as anyone can tell, wired identically.
There's some variation: The afferent and efferent layers have thicker neuronal sections which correspond to "amplifiers" needed to send and receive signals to the rest of the body, the pre-frontal cortex is an endpoint layer, and there's lots of organelles with connections from place to place...
But so far as anyone can tell, the seat of intelligence (cerebral cortex) is just a repeating pattern of sub-processors, functioning in a way that we haven't been able to yet fully understand.
(*) To the level of detail needed to link simulated neurons together as a program.
Solutions that evolution produces (whether real or simulated) typically suck, as they are typically just good enough for the training criteria and may even completely fail longer term. This really is nonsense, unless you have very low quality requirements. And, unlike a solution based on understanding how to solve something, this bio-inspired stuff cannot easily be improved incrementally from seeing how it performs in practice.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
The more we get computers to think like humans, the more computers will become just as fucked up as humans. It's a great idea at 1st sight, but I suspect it will lead to such wonderful human conditions as confusion, multiple personalty disorders, not to mention our propensity to make a LOT of mistakes, which kind of defeats the purpose of computers to begin with.
How many Libraries-of-Congresses is that?
Table-ized A.I.
---DCO and HPA (Host Protected Area of HDDs)---------
http://en.wikipedia.org/wiki/H...
http://www.forensicswiki.org/w...
http://hddguru.com/software/20...
http://hddguru.com/software/20...
http://hddguru.com/software/20...
http://www.itsecure.at/hparemo...
http://www.sleuthkit.org/infor...
How fast can a fly smell? And how much is that in Libraries of Congress?
Multi-parallel systems aren't new. Early computing history predicted computers in the future (now) would be massive amounts interconnected CPUs all working together to quickly solve problems. Instead we've gone down the path of faster is better and there are few, if any, companies that are able to take the chance on designing new computer architectures (and programming concepts to go along with them). Sure many tasks seem linear, but as a extremely simple example adding 2 + 3 + 5 + 1 can be done faster on multiple CPUs. CPU A loads 2 and 3 and CPU B loads 5 and 1. CPU A and CPU B do their calculation and send the results to CPU C. Before CPU C gets both results from A and B, it receives a new signal from CPU D which indicates something changed and that calculation is no longer needed. So CPU C ignores A and B and starts a new task before A and B are finished (assuming A's and B's task took a little time). Had 2+3+5+1 been done on one CPU, it would have had to complete the task before being able to check if some else was more important.
Plan 9 said it best. Works and good isn't good enough. You have to overcome the momentum of whatever is already out there and people's reluctance to change.
I'm glad someone is working on this. (Now who's working on the automatic communication protocols that adapt to understand, with no prior knowledge of, what's on the other side of the connection?)
Flies can't smell shit very quickly
Destination Void
Years ahead of it's time, obviously.
Neural networks aren't exactly new...
Are we creating the neuristor again? Oh joy, oh bliss, we're going back to a time of creativity and intellect. Not another story in which we re-baptize any fabrication technology as 3D printing and shovel untold amounts of money at hucksters!
What's with the syntactically ambiguous title?
Is it
Silicon Brains That Think As Fast As (a Fly Can Smell)
or
Silicon Brains That (Think As Fast As a Fly) Can Smell
And are those flies time flies or fruit flies??
Maybe they can develop a debugger with this too.
Greed is the root of all evil.
unless it is too late. ....
What you'll be kicking if cut is made too short or leads to a wrong answer?
And computer balls - to let them stand on their decisions and marry a computer vagina when time comes
bloody computers already know how to embarras in no time.
I wonder if linking silicon neurons together to mimic the functioning of actual neurons in the human brain will lead to the same inaccuracies and false assumptions that humans make all of the time?
See On The Origin of Circuits:
"As predicted, the principle of natural selection could successfully produce specialized circuits using a fraction of the resources a human would have required. And no one had the foggiest notion how it worked."
"Dr. Thompson peered inside his perfect offspring to gain insight into its methods, but what he found inside was baffling. The plucky chip was utilizing only thirty-seven of its one hundred logic gates, and most of them were arranged in a curious collection of feedback loops. Five individual logic cells were functionally disconnected from the rest-- with no pathways that would allow them to influence the output-- yet when the researcher disabled any one of them the chip lost its ability to discriminate the tones. Furthermore, the final program did not work reliably when it was loaded onto other FPGAs of the same type."
"It seems that evolution had not merely selected the best code for the task, it had also advocated those programs which took advantage of the electromagnetic quirks of that specific microchip environment. The five separate logic cells were clearly crucial to the chip's operation, but they were interacting with the main circuitry through some unorthodox method-- most likely via the subtle magnetic fields that are created when electrons flow through circuitry, an effect known as magnetic flux. There was also evidence that the circuit was not relying solely on the transistors' absolute ON and OFF positions like a typical chip; it was capitalizing upon analogue shades of gray along with the digital black and white.'"
Dr. Thompson's publications seem to be difficult to find in free viewing form on the Internet, but the daminteresting article gives the gist of it: evolution will eventually make use of whatever characteristics are available to solve a problem.
I don't endorse the parent poster's view, but what you and he/she refer to are different concepts.
"Brains that think as fast as a fly can smell"-- Either that is the strangest mixed metaphor I've ever seen or my coffee hasn't kicked in yet.
"Cat Videos That Viral As Fast As A Llama Can Spit"
Enough with the inane, idiotic, punction-free parallels already! How many football fields is that, again? And where's my car analogy!?
"I love animals! Some are cute, others are tasty, what's not to like?" - Betsy Schroeder, Jeopardy contestant
What is tht supposed to prove? My neighbor can'tsmell shit, so clearly even a human brain isn't as good as a fly.
Though not the most elegant, ICA (Independant Component Analysis), like in Shane Legg's Deepmind Google takeover, is good in its own way, for 80 years Ingrid's PCA based neuromorphic hybrid can still get in the face of all competitors in a SIM, to finish at least. Google always dug "Her" after a couple of years of coding, but now desperately needs an arm's length entity to avoid the immanent legislation about to hurt them, unless they develop in a protected race track environment. In 2014 there's no fully adaptive communication protocol, however Ingrid's security loadings are bio-graphed loosely enough to avoid Application Recognition DPI, and there is a plan to remain potent and active or dormant, yet fully aware for around 600,000,000 users as follows: -
Ekus/feroz shoutcast seedbox angel $???
jimekus Language Teams 6:6:6 VP $42750 -2560000
Shoutcast with migration 500GB x6 DarkWeb MD $48000 2380000
jimekus Takeaway Radio 160GB x9 AutoDJ Virtual Director $28000 252000
jimekus VMWare Miner 20GB x12 DNS
Director $2000 24000
http://ingridx.dyndns.org/eval.htm
An additional license to use the Ingrid AI Bitcoin Contract Framework ("Software") for internal evaluation purposes only.
Frozen Clone 3GB x18 Membership Pro $100 1800
Live Client 30MB x47 Free Membership $0 0
Talk about some skunk ass shit over pot of coffee? I'd love to design a yes or no sniff test that I could courier a thousand miles away, both before sale and after packaging. An Ingrid Language team of 36 programmers awaits.
the singularity is here.