[RELEASE]
[IMG]http://www.techeye.net/assets/upload/humanbrainlead.jpg[/IMG]
A project to replicate the workings of the human brain has received a boost with the delivery of one million ARM processors.
While Intel has its sights set on reaching bumble bee brain level in the near future, it seems its rival is involved in one further.
Scientists at the University of Manchester will link together the ARM chips as the system architecture of a massive computer, dubbed SpiNNaker, or Spiking Neural Network architecture.
Despite the mass of chips it will only be possible to recreate models of up to one percent of the human brain.
The chips have arrived and are past functionality testing.
A similar experiment was once attempted with a load of old Centrino chips found at the back of our stationary cupboard, though so far we haven't even managed to replicate the cranial workings of a particularly slow slug.
The work, headed up by Professor Steve Furber, has the potential to become a revolutionary tool for neuroscientists and psychologists in understanding how our brains work.
SpiNNaker will attempt to replicate the workings of the 100 billion neurons and the 1,000 million connections that are used to create high connectivity in cells.
SpiNNaker will model the electric signals that neurons emit, with each impulse modelled as a ‘packet’ of data, similar to the way that information is transferred over the internet.
The packet is sent to other neurons, represented by small equations solved in real time by ARM processors.
The chips, designed in Machester and built in Taiwan, each contain 18 ARM processors.
The bespoke 18 core chips are able to provide the computing power of a personal computer in a fraction of the space, using just one watt of power.
Now that the chips have arrived it will be possible to get cracking on building model.
“The project revolves around getting the chips made, which has taken the past five years to get right,” Professor Steve Furber told TechEye.
“We will know be increasing the scale of the project over the next 18 months before it reaches its final form, with one million processors used. We already have the system working on a smaller scale, and we are able to look at fifty to sixty thousand neurons currently.”
As well as offering possibilities as a scientific research tool, Furber hopes that the system will help pave the way for computational advancements too.
“It will help to analyse the intermediate levels of the brain, which are very difficult to focus on otherwise,” he says.
“Another area which this help is in building more reliable computing systems. As chip manufacturers continue towards the end of Moore’s Law, transistors will become increasingly unreliable. And computer systems are very susceptible to malfunctioning transistors.”
Furber says biology works differently. “Biology, on the other hand, reacts to the malfunctioning of neurons very well, with it happening regularly with all brains, so this could help future chips become more reliable.”
Of course, we also wanted to know how this all compares with Intel’s famous bumblebee claims.
Unfortunately, professor Furber couldn't specifically help us with information about bumblebee brain processing.
He was, however, able to reel off some details about the honeybee.
“The honeybee brain has around 850,000 neurons so we will be able to reach that level of processing in the next few months. Of course, we don’t have a honeybee brain model to run, but we will have the computing power.”
Over to you, Intel.
Read more: [url]http://www.techeye.net/chips/one-million-arm-chips-challenge-intel-bumblebee#ixzz1T4PxXYro[/url]
[/RELEASE]
Source: [url]http://www.techeye.net/chips/one-million-arm-chips-challenge-intel-bumblebee[/url]
Looks like the article got a typo:
[quote]The chips, designed in [B]Machester [/B]and built in Taiwan, each contain 18 ARM processors.[/quote]
I thought that we were able to emulate, at least slowly, up to a cat's level of intelligence.
[QUOTE=ASmellyOgre;31315913]I thought that we were able to emulate, at least slowly, up to a cat's level of intelligence.[/QUOTE]
Well, 1% of the human brain is roughly equivalent to the rat's cerebellum they emulated with the Blue Brain project.
We need more computing power.
Also the IBM claims were a hoax, they emulated a bunch of "dots" whose structure and internal functions had no resemblance at all with the neurons of a cat.
Stop building SkyNET you doombringers
Just from reading the article, it just sounds like its a crapload of CPUs that throw packets at each other.
Umm... ok, any cluster can do that you don't need a millions cpus.
I'm fairly certain you have to know how the brain works to create this sort of model. It's not like CPUs are gonna spit out the answers to life when you hook up one million of them.
[QUOTE=PvtCupcakes;31316184]Just from reading the article, it just sounds like its a crapload of CPUs that throw packets at each other.
Umm... ok, any cluster can do that you don't need a millions cpus.
I'm fairly certain you have to know how the brain works to create this sort of model. It's not like CPUs are gonna spit out the answers to life when you hook up one million of them.[/QUOTE]
You don't need to comprehend how the brain works to model it, "all" you need is understanding of the information processes of the very, very low level dynamics, then map those regions and implement them.
EDIT: Moreover, the Blue Brain project emulated a part of a rat's brain and all the real-life input/output matched the virtual input/output, how fucking amazing is that?
I would hate to have the job of going through a million processors and testing them all.[QUOTE=Joazzz;31316060]Stop building SkyNET you doombringers[/QUOTE]No.
We need.
a thousand factories.
working 25/8.
and delivering 25/8.
Y'know, whilst all this is amazing stuff, I honestly wonder why we haven't been finding a way to sustain a living brain in a jar, then use said brain-in-a-jar as a sort of organic CPU.
On second thought, we'll probably be able to do that later when we work out how to keep a brain on life support outside the body, or if we end up having a close encounter with the Mi-go.
[QUOTE=Sobotnik;31316274]We need.
a thousand factories.
working 25/8.
and delivering 25/8.[/QUOTE]
Oh you don't need something as crude, according to Eir Metamajesty the Lord Kurzweil by 2029 our factories will be printing the equivalent of a human brain on silicon oxide, so all you have to do is wait two decades.
[QUOTE=Eudoxia;31316309]Oh you don't need something as crude, according to Eir Metamajesty the Lord Kurzweil by 2029 our factories will be printing the equivalent of a human brain on silicon oxide, so all you have to do is wait two decades.[/QUOTE]
Not enough.
Pour loads of money into inventing the damn things faster.
And machines to build the machines that will mass produce the machines to mass produce the parts faster.
[QUOTE=Sobotnik;31316274]We need.
a thousand factories.
working 25/8.
and delivering 25/8.[/QUOTE]
[img]http://imgs.xkcd.com/comics/28_hour_day.png[/img]
Of course, factories can be open all of the time. This only applies to the workers.
[QUOTE=Sobotnik;31316369]Not enough.
Pour loads of money into inventing the damn things faster.
And machines to build the machines that will mass produce the machines to mass produce the parts faster.[/QUOTE]
Chemical reactions happen only so fast and photolithography can only go so far.
[QUOTE=Eudoxia;31316247]You don't need to comprehend how the brain works to model it, "all" you need is understanding of the information processes of the very, very low level dynamics, then map those regions and implement them.
EDIT: Moreover, the Blue Brain project emulated a part of a rat's brain and all the real-life input/output matched the virtual input/output, how fucking amazing is that?[/QUOTE]
If you know that much about the brain, you can do it in software.
It might not be amazingly fast in software, but the whole 1 CPU = 1 nueron thing is kind of silly.
Well at least then Mancunians(is that the right word?) will have some form of intelligence.
[QUOTE=shatteredwindow;31316644]Well at least then Mancunians(is that the right word?) will have some form of intelligence.[/QUOTE]
cooool! i live there its sickest thing eva!!!!!
[QUOTE=]While Intel has its sights set on reaching bumble bee brain level in the near future, it seems its rival is involved in one further.[/QUOTE]
The increased competition in this and related fields is a wonderful thing.
They should make these.
[img]http://www.empireonline.com/images/features/100greatestcharacters/photos/63.jpg[/img]
It's simulation of human brain so I think that calling it Artificial Stupidity would be more fitting.
[QUOTE=Kurtzund;31317576]They should make these.
[img]http://www.empireonline.com/images/features/100greatestcharacters/photos/63.jpg[/img][/QUOTE]
[url]http://www.facepunch.com/threads/1110395[/url]
[QUOTE=Sobotnik;31316369]Not enough.
Pour loads of money into inventing the damn things faster.
And machines to build the machines that will mass produce the machines to mass produce the parts faster.[/QUOTE]
This man is onto something..
[QUOTE=PvtCupcakes;31316591]If you know that much about the brain, you can do it in software.
It might not be amazingly fast in software, but the whole 1 CPU = 1 nueron thing is kind of silly.[/QUOTE]
It's to further emulate structure in an actual physical form. Even when you do emulate brain structure virtually, you'll still need a myriad of processors, even for a small portion of brain power.
Who ever teaches it first wins
[QUOTE=Sobotnik;31316369]
And machines to build the machines that will mass produce the machines to mass produce the parts faster.[/QUOTE]
How did you hear about me liking machines?
[QUOTE=ironman17;31316297]Y'know, whilst all this is amazing stuff, I honestly wonder why we haven't been finding a way to sustain a living brain in a jar, then use said brain-in-a-jar as a sort of organic CPU.
On second thought, we'll probably be able to do that later when we work out how to keep a brain on life support outside the body, or if we end up having a close encounter with the Mi-go.[/QUOTE]
i dont think getting a brain to live outside the human body is the hardest part, i think having it be able to interact with anything is the hardest part
Then link it up to the world's nuclear weapon systems.
will you be able to play crysis on it?
[QUOTE=Awesomecaek;31317644]It's simulation of human brain so I think that calling it Artificial Stupidity would be more fitting.[/QUOTE]
You just insulted yourself
18 core chips? Imagine using that kind of hardware!
Sorry, you need to Log In to post a reply to this thread.
