Slashdot Mirror
SpiNNaker Powers Up World's Largest Supercomputer That Emulates a Human Brain
The world's largest neuromorphic supercomputer, the Spiking Neural Network Architecture (SpiNNaker), was just switched on for the first time yesterday, boasting one million processor cores and the ability to perform 200 trillion actions per second. HotHardware reports: SpiNNaker has been twenty years and nearly $19.5 million in the making. The project was originally supported by the Engineering and Physical Sciences Research Council (EPSRC), but has been most recently funded by the European Human Brain Project. The supercomputer was designed and built by the University of Manchester's School of Computer Science. Construction began in 2006 and the supercomputer was finally turned on yesterday.
SpiNNaker is not the first supercomputer to incorporate one million processor cores, but it is still incredibly unique since it is designed to mimic the human brain. Most computers send information from one point to another through a standard network. SpiNNaker sends small bits of information to thousands of points, similar to how the neurons pass chemicals and electrical signals through the brain. SpiNNaker uses electronic circuits to imitate neurons. SpiNNaker has so far been used to mimic the processing of more isolated brain networks like the cortex. It has also been used to control SpOmnibot, a robot that processes visual information and navigates towards its targets.
SpiNNaker is not the first supercomputer to incorporate one million processor cores, but it is still incredibly unique since it is designed to mimic the human brain. Most computers send information from one point to another through a standard network. SpiNNaker sends small bits of information to thousands of points, similar to how the neurons pass chemicals and electrical signals through the brain. SpiNNaker uses electronic circuits to imitate neurons. SpiNNaker has so far been used to mimic the processing of more isolated brain networks like the cortex. It has also been used to control SpOmnibot, a robot that processes visual information and navigates towards its targets.
20 years
20 million dollars
more like 20 billion dollars
bunch-o-liars
...that the article does not mention that the project lead, Steve Furber was one of the team at Acorn that created the original ARM chip back in the 80s.
Or as it is generally known, computer cluster.
Which is it, genius editors ?
And with only million cpu's, isn't that a few orders of magnitude to small to emulate a human brain anyways, which has hundreds of billions of neurons?
File under 'M' for 'Manic ranting'
Since we now know that this really matters?
https://www.sciencealert.com/science-discovers-human-brain-works-up-to-11-dimensions
With a Touring Test
If you have a piece of software that can pass a touring test what have you really created and what does it say about the nature of intelligence ?
With this
It would seem that it just validates (not a small thing) the knowledge of how an animal brain is put together, and only in very limited ways at that.
Overall I suspect this project will tell us much more about what we don't know about how brains are put together than what we do know about how thought works.
In all honesty, I doubt it'll go much beyond the 250,000 neuron mark. Brain simulators tend to also be very slow, the ones I could find on Google could take a few hours to simulate a second of activity.
Based on the core count versus simulation speed versus neurons, a simulator that could handle the whole brain at one second per second would be five miles in diameter and 1,500 feet high.
That doesn't mean this simulator is unimportant. Simulating fractions of the brain in extended time will let neurologists see the effects of medical interventions. That, and not HAL, is the objective of such projects, after all.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
The only thing I want a spiNNaker to power is my goddamn sailboat.
If anyone else is wondering how they can afford a million cores with a budget of less than 20 million dollars: Wikipedia says they are some ARM cores in 10 19 inch racks.
Each core is supposed to be able to simulate 1000 neurons.
Sure, this will definitely help us understand the brain and probably AI in general, but don't mistake it for an "electronic brain" on the level of a humans as some people are doing, either for fun or in ignorance.
Also, don't forget that our wetware already has a lot of programming in it by default, and we don't even pretend to be able to read and comprehend that source code. So even if we did do a good duplicate of the brain, it's just not going to be the same.
A further complication that may invalidate a lot of this digital mimicry is the sheer complexity of the human brain.
Yes, we all know it's big and complex, but they are just starting to figure out that even the tiny bits are more than a bit. One type of brain cell (there are several different types, and they each do different things) appears not to be the equivalent of a bit in a computer as people have talked about before, and it might not even be a qubit as more recent discussions have gone over!
Some work in the past couple of years has identified structures that might make each of those cells in our brains be the equivalent of many quibits in a quantum processor! (I don't remember the exact number, but I'm pretty sure it was somewhere between 10 and 20 each cell.)
If that's correct, it increases the relative computing power of the human brain to insane levels that no regular computer can ever duplicate. Even a quantum computer would have to have far more processing than anything we've possible built so far. I say possibly built because the quantum processors out there are suspected by some of not actually being quantum processors.
The project is still important, and will likely yield very valuable research material, but the whole sci-fi electronic brain is still a looooong way off.
An 8 core ARM TV Box, costs me $59, less than $8 per core including all the support circuitry, network, flash, ram....... RETAIL. Literally I walked into a shop and bought everything on their shelf for less than $2000 to form my cluster.
They're insanely cheap.
I guess these lot spend $2/core for the ARM chip and the rest is all overhead.
Yeah, but can it play doom?
Wanna buy a shirt?
https://www.redbubble.com/people/stealthfinger/shop?asc=u
Homophones, Homographs, Homonyms all a pain in the ass.
If your so-called brain was switched on yesterday, it would also be useless today. Just like a baby on the first day, if said baby had no genetically pre-determined structures whatsoever, and everything was still random.
You do realize, we ourselves need years, to do something worth reporting, beyond that which was in our genes from the start?
SpiNNaker may need years too, to get to any higher function. Unless they pre-set it via non-NN methods. (And then I bet you’d call them cheaters.)
The editors have not used it yet. I mean their own....
... which babies can be quite good at!
Its now known that the white matter in the brain isn't passive after all and does affect information processing, plus the neurons are also affected by "out of band" (for want of a better term) signals in the form of hormones. So unless you simulate all of that then at best it'll be a brain-lite even if they simulated all 100 billion neurons (which I very much doubt).
Takes real brains to get in here like this!
200 tflops, boring
Well yeh, I assumed they didn't just walk down the shop and buy some TV boxes!
1 amp to run 64 cores.... literally a USB powered super computer in each board. FFS.
"The 103 machine is the 48-node board and has 864 ARM processor cores, typically deployed as 768 application cores, 48 Monitor Processors and 48 spare cores. The 103 machine requires a 12V 6A supply. The control interface is two 100Mbps Ethernet connections, one for the Board Management Processor and the second for the SpiNNaker array. "
Jealous.
They don't need to do Journalism 101, they need to do Journalism 000 "Don't write complete nonsense that contradicts itself"
"Skynet becomes self-aware at 02:14 am Eastern Time after its activation on Nov. 4, 2018 and immediately begins shitposting on 4chan."
"Slow down, Cowboy! It has been 3 years, 7 months and 26 days since you last successfully posted a comment."
They're just adjusting to the Trump era...
Because between the "yesterday" referenced in the article when they "turned it on for the first time" and the "now" when the article was written there wasn't enough time to use the machine in any form or function, right? It's just sitting there...idle...like a giant fucking paperweight and does absolutely fucking nothing. Or maybe there might actually be enough time in the 12 - 24 hrs that differentiates "yesterday" from "today" that they could have spun up some simulations that they had ready to go.
BTW... It's the Article, not the editors, that specified the so called contradiction that really doesn't fucking exist you disingenuous fuck.
BrainCoin... we need it... simulate brain functions on the blockchain with a massive crypto network, but instead of crypto, do brain stuffs.
Get rewarded with BrainCoin. Someone can surely spin that up since any idiot with a PC at home can apparently spin up a crypto network.
You say 20 years in-the-making ... and a CS department is ramrodding the project ?? Jeeez Louise in 2002 CPU's were electro-mechanical and pipelines fluid. Hard-drives .. busting that 60 Mb threshhold. Yep , a smooth 20 year connection ... like the Andrew sisters, Jan & Dean and Beiber ... not an abortion run wild! Has the new chip discovered BRIDGE ?
Understand the words you're trying to use:
emulate VERB
computing
reproduce the function or action of (a different computer, software system, etc.).
simulate VERB
imitate the appearance or character of.
produce a computer model of.
They are not interchangeable.
"A neuron is much simpler than a cpu" - I don't think you're up to speed on the complexity and adaptability of function within one single neuron.
A neuron performs localized non-linear computations with spiking forward and backward throughout it's 10,000 dendrites, it's not a simple "sum". In addition, the long term state of synapses are maintained due to epigenetic changes in the dna, the neuron is managing all of those synaptic weights. Scientists don't fully understand the function of even one type of neuron (there are many many types).
A single neuron is a very complex thing, probably similar to or more complex than a cpu.
Maybe your contrived idea of what it did actually happened, maybe they are talking crap, maybe they are lying: We don''t know, we are not told, and that means the Editors have failed to Edit.
What a fuckwit.
So in your inspired view of journalism, an Editor can post an article full of nonsense, not mention that it's nonsense or what is wrong with it, and that's okay, because "It's in the 'Article'".
What a fuckwit.
To truely emulate the brain, then memories have to be in each CPU. They have found that neurons now contain our memories, so a true setup would be like teradata DB, than a Von Neumann computer architecture.
I prefer the "u" in honour as it seems to be missing these days.
New info has the axon containing the memory. IOW, a single CPU should be accessing a portion of the memory, as opposed to all CPUs being able to access all memory ( though slowly ).
I prefer the "u" in honour as it seems to be missing these days.
Minsky pushed the idea that multi-layer neural networks were a dead end, missing the fact that a multi-layer neural network is a universal function approximator.
Neural networks are suited for a broad range of problems that symbolic methods are not. Ultimately we will probably end up with a combination of neural + symbolic to achieve real AI. But to even harness the advanced methods that symbolic is well suited for requires that foundation of being able to deal with messy data, categorization and pattern matching first.
First, scientists need to understand what one single neuron does to be able to simulate. Current understanding is that a single neuron is actually more like an entire neural network due to all of the non-linear calcs performed by the 10,000 dendrites (not just sum, it's more complex with local/regional spiking, forward and backward, all kinds of stuff).
Secondly, scientists will need to figure out what exactly glial cells are doing, they control the synapse and manage the action, detecting and releasing neurotransmitters, glialtransmitters, chemical and electrical gradiant controlling more regional sections, etc.
We have no idea how our brains really work, and this toy they built at best could only 'emulate' perhaps an insects' brain.
But emulate is the correct term.
It aims to emulate actual proper synaptic activity, not merely simulate it through hacks.
Honestly, they'd be better off NOT emulating it and actually simulating it.
The human brain, despite being amazingly complex, is horribly shitty.
The issue with computers is they can't emulate the silly amount of parallel activities that they can do.
But parallel processing is not the best for many jobs. In fact, ask a typical human to do a job that is not parallel and watch them struggle where a computer could do it in milliseconds.
Both types of processing are valuable.
Our brain is filled with redundant crap due to the limitations of low-energy biology.
Biology evolved many hacks to get around our pitiful little low-energy planet. You can see that any time you look at optical illusions.
As it is now, even self-driving cars algorithms can be fucked with scotch tape.
Computers don't have that limitation, they can be as power-hungry as they want to be. Obviously it is better to at least aim for efficiency, but they still aren't limited by it. (within reason! Overheating is an issue!)
They can be 100% efficient in processing information whereas the brain is incredibly lossy when it processes sensory inputs. Datasets from your senses are dimension-compressed to hell and back. It was only just the past 10 years we were able to decode how visual information is represented in the brain due to that lossy conversion.
And the most important part, at some point as graphene or better substrate comes along, we will be able to process at speeds at considerably higher frequencies than our puny brains can, both in serial and parallel datasets.
Heard this on NPR a few days ago by someone on the team. They said a mouse brain cause its close to a human brain.
hey anyone know where I can get some really good cheese?
Is it really "incredibly unique"? Damn, that so much more unique than almost every other unique thing! I mean, most unique things are unique, but this thing is apparently incredibly more so.
Mind != Brain. There have been dozens of experiments showing the Non-Locality of Mind..
Citations please...
"Answer" http://www.roma1.infn.it/~anzel/answer.html
by Fredrick Brown https://en.wikipedia.org/wiki/Fredric_Brown
42