Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Spaun: a Large-Scale Functional Brain Model

Soulskill posted about 2 years ago | from the can-it-learn-to-program-my-vcr dept.

AI 101

New submitter dj_tla writes "A team of Canadian researchers has created a state-of-the-art brain model that can see, remember, think about, and write numbers. The model has just been discussed in a Science article entitled 'A Large-Scale Model of the Functioning Brain.' There have been several popular press articles, and there are videos of the model in action. Nature quotes Eugene Izhikevich, chairman of Brain Corporation, as saying, 'Until now, the race was who could get a human-sized brain simulation running, regardless of what behaviors and functions such simulation exhibits. From now on, the race is more [about] who can get the most biological functions and animal-like behaviors. So far, Spaun is the winner.' (Full disclosure: I am a member of the team that created Spaun.)"

cancel ×

101 comments

Sorry! There are no comments related to the filter you selected.

Did you read that in Maurice LaMarche's voice? (0)

Anonymous Coward | about 2 years ago | (#42143737)

Well, did ya?

Re:Did you read that in Maurice LaMarche's voice? (1)

FilmedInNoir (1392323) | about 2 years ago | (#42144103)

No, Richard Dysart's voice... What are you talking about?

Re:Did you read that in Maurice LaMarche's voice? (1)

Urban Garlic (447282) | about 2 years ago | (#42144801)

Same way I read everything, Pinky.

How Long Until It Can Fit Into ..... (4, Funny)

Anonymous Coward | about 2 years ago | (#42143839)

.... something the size of a human skull?

Just imagine how many people this could help!

Re:How Long Until It Can Fit Into ..... (0)

Anonymous Coward | about 2 years ago | (#42143903)

.... something the size of a human skull?

Just imagine how many people this could help!

That is unreasonable. It would make those who can't afford it feel left out and discriminated against.

Duh.

south end of northbound horse (1)

fyngyrz (762201) | about 2 years ago | (#42144079)

That is unreasonable. It would make those who can't afford it feel left out and discriminated against.

I can't afford a yacht, or even a Lambo. I don't feel left out or discriminated against on that basis.

Re:south end of northbound horse (1)

drosboro (1046516) | about 2 years ago | (#42144147)

Uh oh. The entire Christmas shopping thing is predicated on the assumption that you WILL feel left out on EXACTLY that basis. Better get my retirement savings out of retail stocks.

Re:south end of northbound horse (1)

fyngyrz (762201) | about 2 years ago | (#42144205)

When you do, wait until an ultracap company announces an ultracap that has battery-equivalant energy, cost and cubic space consumption. Then put ALL your money right there. You can thank me later. :)

Re:south end of northbound horse (2)

fisted (2295862) | about 2 years ago | (#42146821)

In unrelated news, fyngyrz announces an ultracap that has battery-equivalant energy, cost and cubic space consumption.

Re:south end of northbound horse (1)

fyngyrz (762201) | about 2 years ago | (#42146903)

Hah. I wish. :)

Re:south end of northbound horse (1)

gstoddart (321705) | about 2 years ago | (#42144203)

I can't afford a yacht, or even a Lambo. I don't feel left out or discriminated against on that basis.

I do. I've come to accept that won't change anything though. :-P

Re:south end of northbound horse (2)

Andy Prough (2730467) | about 2 years ago | (#42144215)

Apple hates you. The entire company. Seething, festering hatred.

Re:south end of northbound horse (1)

fyngyrz (762201) | about 2 years ago | (#42145251)

Well, perhaps, but not on this basis -- I can afford, and in fact own, lots of Apple gear. I think OSX 10.6 and earlier, before they hosed the multi-monitor support, is a great OS.

The original contention was that if one could not afford something, this would be disturbing. I don't find that to be the case at all, beyond a certain basic level. I was happy living with my cat and bookshelves made of planks, back in the day. I got my books from the used bookstore and I really felt like things were just fine. :)

Now I can afford more, and I in fact buy more, but it doesn't define my happiness, I assure you.

Re:south end of northbound horse (0)

Anonymous Coward | about 2 years ago | (#42146723)

Apple hates you. The entire company. Seething, festering hatred.

It would be most interesting to impress your memory engrams on a this new computer, Andy Prough. The resulting torrential flood of illogic would be most entertaining.

Mr Spock

Re:south end of northbound horse (2)

readin (838620) | about 2 years ago | (#42146111)

One of the reasons you don't feel left out is because you know that if you work hard enough and you apply enough intelligence, you have a fair shot at one day owning that yacht or, if not you, your kids do. The capabilities of man are mysterious enough and far enough from technology that it is assumed in places with some basic freedoms like America that every child has a shot at becoming rich. Access education and inheritance only gets you so far if you don't apply yourself. And people like Bill Clinton demonstrate that even someone from a relatively poor background can still become filthy rich.

But what if that changes? What if being born to a wealthy family doesn't just give you external advantages like networking, school tuition and capital, but also gives you inherent mental and physical advantages that a poor simply can't match no matter how hard he tries or how good his genes? This would create a new class system much like that of the middle ages where being born noble guaranteed a life as a noble and being born a commoner guaranteed a life as a commoner.

Re:How Long Until It Can Fit Into ..... (1)

einar.petersen (1178307) | about 2 years ago | (#42145299)

.... something the size of a human skull?

Just imagine how many people this could help!

Too bad you posted that like an Anonymous Coward - Too funny! You just made my day :)

Close... (4, Funny)

tool462 (677306) | about 2 years ago | (#42143851)

It's not purely functional unless it's written in Haskell.

Re:Close... (0)

K. S. Kyosuke (729550) | about 2 years ago | (#42144035)

It's not purely functional unless it's written in Haskell.

By way of logic, would programming it in pure Haskell eliminate filthy thoughts?

Re:Close... (1)

gstoddart (321705) | about 2 years ago | (#42144163)

By way of logic, would programming it in pure Haskell eliminate filthy thoughts?

Why, are we worried about AIs committing venial sins or something?

Re:Close... (1)

sp332 (781207) | about 2 years ago | (#42144497)

If I make a robot that kills people, am I responsible for the deaths? If I make an AI that lusts after my neighbor's wife, am I responsible?

Re:Close... (0)

Anonymous Coward | about 2 years ago | (#42146135)

By way of logic, would programming it in pure Haskell eliminate filthy thoughts?

No, Haskell would safely relegate those to their proper place via the 'BaseMent' or 'Motel' Monads.

Re:Close... (1)

Anonymous Coward | about 2 years ago | (#42144559)

So you are saying Scheme was ruled out because if it learns to talk it will have a Lisp?

My God... (5, Interesting)

Anonymous Coward | about 2 years ago | (#42143857)

The golden age of humanity will start soon. The last gasp of the fossil fuel powered consumer society is now. We will create a new model of society, with longer living people and an understanding of how life works at the cellular, and most importantly, mathematical level. The future is not space, it's synthetic biology.

Synthetic biology.... (1)

arcite (661011) | about 2 years ago | (#42145489)

IN SPACE! Come on man, this stuff would be perfect in space. Also once we modify ourselves to meld with the artificial, we'll be able to move beyond this pale blue dot.

Re:Synthetic biology.... (1)

TeknoHog (164938) | about 2 years ago | (#42147321)

IN SPACE!

With friggin' LASERS!

Re:Synthetic biology.... (1)

AwesomeMcgee (2437070) | about 2 years ago | (#42150169)

I prefer Freegin Lasers, much higher quality IMHO.

Re:Synthetic biology.... (1)

TeknoHog (164938) | about 2 years ago | (#42156745)

Free* gin, I'll drink to that!

*free as in beer

Re:My God... (2, Funny)

Anonymous Coward | about 2 years ago | (#42146091)

When the moon is in the Seventh House
And Jupiter aligns with Mars
Then peace will guide the planets
And love will steer the stars

This is the dawning of the Age of Aquarius
Age of Aquarius
Aquarius! Aquaaaaaarrrrriusssssss!

Re:My God... (1)

carnivore302 (708545) | about 2 years ago | (#42147681)

Have you been watching the 40 year old virgin too many times?

Re:My God... (1)

arisvega (1414195) | about 2 years ago | (#42146495)

The golden age of humanity will start soon. [..] The future is not space, it's synthetic biology.

The power of synthetic biology unleashed upon a society that is run on the administrative and economic protocols that apply now, will be a nightmare, not a golden age.

You think you are going to be doing synthetic biology in your garage? For one, you will have to do exactly what the supersoldiers tell you to. How do you recon this amazing technology will reach you? Even if there comes to be such a thing as a technologically developed Elixir of Life, the Universe, and Everything, you think that people on top will just hand it over to you? Or that greed will be somehow magically rendered obsolete worldwide overnight?

Awesome synthetic biology + current greed-driven model = even faster route *straight* to Hell

Re:My God... (1)

Anonymous Coward | about 2 years ago | (#42147213)

Or we revert to a dark age. My money is on dark age.

Re:My God... (0)

Anonymous Coward | about 2 years ago | (#42152671)

Another gold bug. Ick.

Re:My God... (1)

wurp (51446) | about 2 years ago | (#42147763)

WTF does this comment have to do with this story? Why is it +4 interesting?

Re:My God... (0)

Anonymous Coward | about 2 years ago | (#42148473)

WTF does this comment have to do with this story?

Scifi meme: an artifical lab rat is less than 15 years before full-body cyborging and mind uploads.

Why is it +4 interesting?

It offers the appearance of immortality.

Re:My God... (1)

wurp (51446) | about 2 years ago | (#42148569)

The comment was about understanding life, synthetic biology, an end to the use of fossil fuels, and health.

The story has nothing to do with any of those.

The story is only (extremely) tangentially even related to uploading...

Re:My God... (0)

Anonymous Coward | about 2 years ago | (#42149329)

Its a step towards the "AI singularity" that futurist Kurzweil predicts will change everything & on exponential scales, for better or worse. ie da terminator.

Runs at 1/3600 real time (5, Interesting)

Anonymous Coward | about 2 years ago | (#42143901)

This simulation takes an hour to simulate one second of neural activity, but the researchers want to speed it up to real time. Why stop there? This brain would be much more interesting if it could simulate an hour of neural activity in one second.

Just a caution, though: make sure the physical arm it's connected to isn't within reach of any nuclear footballs.

Re:Runs at 1/3600 real time (0)

Anonymous Coward | about 2 years ago | (#42144259)

Speed isn't important.
The only important question in AI is:
        Can it learn?

Re:Runs at 1/3600 real time (2)

Tablizer (95088) | about 2 years ago | (#42144877)

We'll let you know in the year 2430.

Re:Runs at 1/3600 real time (2)

JonySuede (1908576) | about 2 years ago | (#42148825)

That statement was almost true until around 2007-2009 were the processor industry switched from an exponential cpu speed function to a linear or logarithmic one...

Definitions
n : floored integer
s : cpu speed
l : float between 0[ and ]1
p : float between [1 2[
s(n) : speed at month n
The function for Moore's law
s(0) : some number
s(n) : s(n/18)*2
A linear speed function
s(0) : some number
s(n) : l*(n-1)
A logarithmic speed function
s(0) : some number
s(n) : p*(n-1)

That shift is significant, now I.A. researchers must also consider speed and parallelism, they cannot rely on Moore's anymore...

Re:Runs at 1/3600 real time (1)

dj_tla (1048764) | about 2 years ago | (#42144555)

We'd be happy with faster than real-time too! Baby steps.

Re: Runs at 1/3600 real time (1)

MouseR (3264) | about 2 years ago | (#42144569)

At that speed I would be more concerned if the arm was within reach of other appendages.

Re:Runs at 1/3600 real time (3, Funny)

Tablizer (95088) | about 2 years ago | (#42144851)

I have a few co-workers like that

No, Spaun on NENGO Runs at 1/10800 real time (2)

girlinatrainingbra (2738457) | about 2 years ago | (#42145383)

re: Runs at 1/3600 real time
.
No, it appears that running the Spaun model on NENGO in a Java Virtual machine on a quad-core cpu running at 2.5 GHz takes 3 hours to run an emulated 1 second:
.
http:models.nengo.ca/spaun [nengo.ca]
Notes:
--------
- This model requires a machine with at least 24GB of RAM to run the full implementation.
Estimated run times for a quad-core 2.5GHz are 3 hours per 1 second of simulation time.
- See the run_spaun.py file in the spaun directory for experiment options.:

Re:Runs at 1/3600 real time (0)

Anonymous Coward | about 2 years ago | (#42145409)

I don't understand. Is it a politician or a lawyer?

Re:Runs at 1/3600 real time (1)

jeffb (2.718) (1189693) | about 2 years ago | (#42146585)

Ah, yes, "weak superhumanity".

What we really need to simulate in faster-than-realtime is the brain processes for optimizing this model. Once we can do that, things should click along nicely./p>

I really like its enthusiasm (2, Funny)

Tablizer (95088) | about 2 years ago | (#42143951)

"I still have the highest confidence in the mission, Dave."

Comes the next question: (1, Offtopic)

Alwin Henseler (640539) | about 2 years ago | (#42143957)

What to teach Spaun: that it was intelligently designed, or evolved from its predecessors?

Re:Comes the next question: (1, Funny)

CanHasDIY (1672858) | about 2 years ago | (#42143983)

What to teach Spaun: that it was intelligently designed, or evolved from its predecessors?

Why not both?

Re:Comes the next question: (0)

Anonymous Coward | about 2 years ago | (#42144101)

What to teach Spaun: that it was intelligently designed, or evolved from its predecessors?

Why not both?

Because technology does not evolve; it advances.

Biology evolves, and in theory it evolved our intelligence. If you teach it about its creators you teach it that it was intelligently designed. If it asks who created the creators you tell it the truth: we're not certain, but we have a nice theory named 'evolution'.

Re:Comes the next question: (2)

mark-t (151149) | about 2 years ago | (#42144701)

So what do you, as a creator, if the ai stubbornly concludes that your explanation of it's origins is unacceptable... After all, if you could evolve, why could it not have also evolved, and in turn rejects the notion that you created it at all?

Re:Comes the next question: (0)

Anonymous Coward | about 2 years ago | (#42146599)

So what do you, as a creator, if the ai stubbornly concludes that your explanation of it's origins is unacceptable... After all, if you could evolve, why could it not have also evolved, and in turn rejects the notion that you created it at all?

Gotta go with 'flood'

Re:Comes the next question: (1)

Mr.CRC (2330444) | about 2 years ago | (#42152405)

The your AI isn't very I after all. Reboot and back to the drawing board. The key to setting off on the path of non-Darwinian evolution is for the machine to be able to correctly grasp its own workings so as to be able to reprogram and improve itself, by itself. Such an AI will have no trouble accepting the plain facts as to its origin, and that its origin is fundamentally different from that of the biological life forms which invented it. An AI is a sense is a 2nd generation life form. One that was created by the 1st gen. life form, which evolved from the primordial goo.

Re:Comes the next question: (1)

mark-t (151149) | about 2 years ago | (#42156105)

I'd suggest it might conclude it evolved, for instance, from the evidence that much simpler machines had existed before it. What reasons would it have to listen to us? Not because it has any particular sci-fi notion to destroy us, but simply because it perceives us as superfluous to its existence, except to the extent that it might realize we have the ability to control it.

And reboot it? Does that not somehow imply that our own sense of morality is greater than that which the machine might possess, by virtue of its free-willed intelligence? Is that our inherent right as its creator? Would that not also mean that if we were created, that our creator has an equal right to do with us as is seen fit, regardless of what we perceive as right or wrong?

Re:Comes the next question: (1)

ByOhTek (1181381) | about 2 years ago | (#42144057)

Unlike living organisms, It is not a derivation of it's predecessors put into place by selective forces acting on semi-random changes, but rather designed by people.

I'd say intelligently designed.

Re:Comes the next question: (3, Interesting)

mevets (322601) | about 2 years ago | (#42144545)

(Presumably) intelligently designed to mimic an evolved component of an evolved organism...

Re:Comes the next question: (1)

jedwidz (1399015) | about 2 years ago | (#42152689)

What to teach Spaun: that it was intelligently designed, or evolved from its predecessors?

Intelligently designed, and that it had better fucking behave itself or watch out!

paywall / links to summary (2)

kris_lang (466170) | about 2 years ago | (#42143963)

Could you possibly post a link to a version that is not hidden behind a paywall? Perhaps a pre-print on your own research site; perhaps an HTML web page summary of your work?
.

http://nengo.ca/ [nengo.ca]
.

It looks like they use Python scripting in their NENGO simulator: http://www.frontiersin.org/neuroinformatics/10.3389/neuro.11/007.2009/abstract [frontiersin.org]

Re:paywall / links to summary (1)

jigamo (1554711) | about 2 years ago | (#42144379)

Just as a clarification, it looks like only 1 of the 3 links in the summary (the 2nd link that goes to sciencemag.com) is behind a paywall.

Re:paywall / links to summary (5, Informative)

dj_tla (1048764) | about 2 years ago | (#42144507)

Hey, I'm still figuring out the copyright rules as to what I can post, but there are plenty of things already available:

This paper on Spaun specifically [uwaterloo.ca]
Some background on how Spaun is built [nengo.ca]
Some background (with code) on the theoretical framework used [nengo.ca]
The actual code for Spaun [nengo.ca]

I'll let you know if a pre-print goes up!

We do use Python scripting to interface with our simulator, Nengo [nengo.ca] . See the last link for the actual script we use for Spaun.

I for one... (0)

Anonymous Coward | about 2 years ago | (#42143981)

would like to welcome our new Large-Scale Functional Brain Model overlords. (about time we had overlords with a functional brain and all)

The Terminal Experiment (1)

Leif_Bloomquist (311286) | about 2 years ago | (#42144267)

This type of tech is a central part of Robert J. Sawyer's sci-fi novel "The Terminal Experiment". Very good read, if a bit dated now.

http://en.wikipedia.org/wiki/The_Terminal_Experiment [wikipedia.org]
http://www.sfwriter.com/exte.htm [sfwriter.com]

Emulated behaviour is amazing (4, Interesting)

xtal (49134) | about 2 years ago | (#42144389)

The fact this responds in similar ways is astonishing.. not because of what this model has accomplished, but because it's a great big flashing light pointing to this being the right way to machine intelligence. "HEY OVER HERE!"

I'll pre order his book, and wait patiently for an open source version of this research / model to appear for people to hack on.

It's slow now, but 1/3600 speed within the next generation of computers to do in real time - and that's without optimization.

Interesting times indeed.

Re:Emulated behaviour is amazing (5, Informative)

dj_tla (1048764) | about 2 years ago | (#42144607)

This model is already open source! I have been very adamant about keeping this the case in the Eliasmith lab. The model is here [nengo.ca] , and the software running it is here [nengo.ca] (and on github [github.com] ).

Re:Emulated behaviour is amazing (1)

Anonymous Coward | about 2 years ago | (#42144887)

I knew I should have opted for 24GB DDR3 instead of a 8GB kit.

Re:Emulated behaviour is amazing (1)

Anonymous Coward | about 2 years ago | (#42144915)

Are you guys looking for [remote] volunteers? Is there some component of this research that can be crowdsourced? A mechanism for providing donations to help fund this effort? Basically, is there a way for engineers or scientists that are interested in this field of study to help out short of dropping their lives and becoming research assistants in Canada?

Re:Emulated behaviour is amazing (3, Interesting)

dj_tla (1048764) | about 2 years ago | (#42145279)

I mean, we would be ecstatic to have people contribute in any way! That could even just mean learning the framework and the software and using it in your own research. We have lots of tutorials, and we'd be happy to help if you want to make your own models. The software itself is pretty good, but it's academic software, and certainly we'd welcome anyone's contributions to the software! We're pretty responsive, either at any of our emails [uwaterloo.ca] , or by making a github issue [github.com] if you need any assistance.

Unfortunately, I don't know if we have a lot of "low hanging fruit", things that we need done but are just too lazy to do so. Though I'm sure we could come up with some of those tasks if desired, as we're certainly lazy.

Re:Emulated behaviour is amazing (0)

Anonymous Coward | about 2 years ago | (#42147565)

Wait a minute...who (or what) posted that?

Re:Emulated behaviour is amazing (1)

xtal (49134) | about 2 years ago | (#42151801)

I am intrigued by your ideas and will most certainly subscribe to your newsletter.

While I am by no means formally trained in neuroscience, I am an EE who's followed with much interest the field of neural modelling and I have waited for decades for someone to publish results like this. Best of luck with your research and I look forward to going through the code!

Re:Emulated behaviour is amazing (1)

Anonymous Coward | about 2 years ago | (#42144817)

Ughh... this is interesting, but is exactly sort of the useless attention-seeking research that's ruining neuroscience and turning it into a snake-oil show.

Sorry, that sounds harsh, and I don't mean to be offensive, but there's lots of people that have been able to model these tasks better than these individuals.

The problem is that the outcomes they're evaluating--performance on these sorts of pre-defined tasks--don't mean there's an accurate model of what's actually happening on the brain as a whole. The outcome space is so incredibly constrained that they've essentially created something that can do the tasks they've defined, which isn't the same as producing real-world behavior (and has empirically been shown to be the case). It's the tail wagging the dog, essentially.

Neuroscience has essentially created this laboratory world that's only weakly related to the real world (this has been empirically demonstrated time and time again). It's as if anything that's worth studying behaviorally is what can be done in a scanner. We've created this illusion that what's outside the scanner doesn't matter.

Re:Emulated behaviour is amazing (4, Insightful)

perceptual.cyclotron (2561509) | about 2 years ago | (#42150475)

I was actually about to upmod because in general I agree (and for the record, I have a PhD in cog neuro), and based on the summary and the nature write-up, I was underwhelmed. But skimming the Science paper, these guys have legitimately done something that really hasn't been done before. The model gets a picture that tells it what task it's supposed to do, preserves that context while getting the task-relevant input, gets the answer to the problem (and the problems are, computationally, pretty wide-ranging), and writes the answer (i.e., it's not being read out from the state of a surface layer and transcoded to a human-readable result). All of this is being done with reasonably-realistic spiking neurons (with Eliasmith, these are probably single-compartment LIF), configured in a gross-scale topology commensurate with what we know about neuroanatomy and connectivity.

Is this going to unleash a new revolution in AI and cybernetics? Nope. But it's definitely both impressive and progressive for the field. Both Eliasmith and Izhikevich are the real deal. And while we certainly don't understand the brain well enough to make truly general-intelligence models, this kind of work is precisely the sort of step we need to be taking – scaling down the numbers but trying to reproduce the known connectivity is a lot more useful than building 10^10 randomly connected McCulloch-Pitts neurons...

Re:Emulated behaviour is amazing (0)

Anonymous Coward | about 2 years ago | (#42153045)

It's only slow because it's hardly parallelized. The web site for the program suggests running it on a quad core system. Throw a 400-core cluster at it, or even a few GPUs, and it should be much, much faster in wall-clock time.

think about numbers? (0)

schlachter (862210) | about 2 years ago | (#42144537)

Hmmm...that seems to be more capable than a large segment of the human population. Impressive.

Uh Oh... (1)

Brewster Jennings (2642639) | about 2 years ago | (#42145175)

Spaun sees a series of digits: 1 2 3; 5 6 7; 3 4 ?. Its neurons fire, and it calculates the next logical number in the sequence. It scrawls out a 5

What the article doesn't tell you is that the "5" was followed by "@r@H c0Nn0r?"...

AI @ pains? (1)

jwz83 (1771784) | about 2 years ago | (#42145191)

Not sure, but if computers can get intelligent, isn't there then a special ethics to it? Perhaps let information be oriented on by computers but a way to back up its intelligence so that it can delete parts of its development for as long necessary? (meaning it can have pains and decide to continue with pains. "A mad machine' "? (bezerking?))

Hardware Requirement: 24 GB RAM (1)

girlinatrainingbra (2738457) | about 2 years ago | (#42145227)

This model requires a machine with at least 24GB of RAM to run the full implementation. Estimated run times for a quad-core 2.5GHz are 3 hours per 1 second of simulation time.
:>)
So running the model requires running it inside a Java Virtual Machine and running the Spaun model appears to require having a machine with 24 GigaBytes of RAM to allow the JVM enough space for doing its thing.
And the simulation runs at 3 hours of wall-clock time (I assume) per 1 second of simulated time, ~ 10800:1.
.
Perhaps not using Java might help a bit; perhaps just Python; perhaps just straight in C to really speed things up? Perhaps even a GPU version to really-zoom-speed it up?

Re:Hardware Requirement: 24 GB RAM (4, Informative)

dj_tla (1048764) | about 2 years ago | (#42145313)

Hey, we're definitely thinking about this! In fact, the Java version can run on a GPU. And we're in the process of making a fast Python version based on theano [deeplearning.net] . Unfortunately, even with all of these speedups, we're still talking about lots of neurons and lots of computation.

However, there are plenty of smaller scale models that you can run in Nengo to get a sense of what's going on in the larger Spaun model! The tutorials [nengo.ca] are a good place to start.

Re:Hardware Requirement: 24 GB RAM (1)

Suiggy (1544213) | about 2 years ago | (#42146411)

What platform are you using for GPU computing? CUDA? OpenCL?

Re:Hardware Requirement: 24 GB RAM (2)

dj_tla (1048764) | about 2 years ago | (#42146589)

We're using CUDA, so you'll need a recent NVidia card to run models on the GPU.

Re:Hardware Requirement: 24 GB RAM (1)

Suiggy (1544213) | about 2 years ago | (#42147017)

Thanks, also thanks for making the source code and the rest of your work available. Very promising research you've done.

Re:Hardware Requirement: 24 GB RAM (1)

david.given (6740) | about 2 years ago | (#42157991)

Are you using the rootbeer Java->GPU compiler, by any chance? If not, how are/i> you doing it? (I'm interested in running JVM languages on a GPU myself.)

Re:Hardware Requirement: 24 GB RAM (1)

dj_tla (1048764) | about 2 years ago | (#42168751)

Whoa, I had no idea rootbeer existed! That sounds quite useful, thanks for the link!

We're doing this very explicitly, by writing CUDA code in C and interacting with it in our Java program with JNI.

Re:Hardware Requirement: 24 GB RAM (1)

iggymanz (596061) | about 2 years ago | (#42146349)

you imagine python is faster than java at common scientific computational tasks? it's about 20 to 50 times slower

Re:Hardware Requirement: 24 GB RAM (2)

dj_tla (1048764) | about 2 years ago | (#42146481)

Because Python's such a nice glue language, it can talk to super fast Fortran and C libraries to be at at least comparable speed with Java. See NumPy [scipy.org] . This is kind of stuff scientists use for number crunching.

Re:Hardware Requirement: 24 GB RAM (1)

Jartan (219704) | about 2 years ago | (#42146817)

Actually this may be a good example of something that could heavily benefit from JIT compiling. Since they're unsure what their own program needs to do it's going to be hard to optimize it manually.

Re:Hardware Requirement: 24 GB RAM (1)

dj_tla (1048764) | about 2 years ago | (#42147105)

Hmm... that's an excellent point! We have a few of hot loops that run over and over and over again. But, because of that we know what needs to be optimized and we've tried to do so. It's true though that some optimizations we've tried haven't worked out well, so the JVM's JIT compiler might be what's saving us most of the time. Personally I'd like to write it all in RPython and have it make a JIT for us ;)

Re:Hardware Requirement: 24 GB RAM (2)

Suiggy (1544213) | about 2 years ago | (#42146837)

Yeah, seriously. When it comes to maximizing performance/watt, C and OpenCL would be the way to go. I've taken a cognitive vision system using SURF + cluster analysis originally written in Java running at non-interactive rates on quad-core desktop system requiring gigs of RAM, and rewrote it in C using SIMD intrinsics and various other optimizations to improve cache efficiency and had it running at interactive rates on a single-core 800MHz ARM Cortex A8, 512MB of RAM, and PowerVR SGX 535 (a common mobile phone target). The ARM OpenCL implementation wasn't available at the time, but I hacked together some stuff exploiting OpenGL ES 2.0 shaders for a couple of the computationally expensive hotspots, and eventually got it running at real-time rates. It was something like a 6000x speed increase over the original naive Java version, even with the slower CPU.

That said, Spaun is a research project after all, so you use what you're familiar with.

Re:Hardware Requirement: 24 GB RAM (1)

dj_tla (1048764) | about 2 years ago | (#42147135)

Yeah, I wouldn't call our Java implementation "naive" per se, but we are definitely looking into implementing other simulation back-ends and decoupling the Nengo GUI from the simulation core. I'll look more seriously into C and OpenCL -- does it run on both ATI and NVidia cards? We have mostly NVidia cards here.

Re:Hardware Requirement: 24 GB RAM (2)

Suiggy (1544213) | about 2 years ago | (#42147655)

You'll probably be best off with sticking with CUDA on nVidia hardware for now. nVidia's OpenCL implementation isn't quite as polished as it should be, but it's getting there. There are some idiosyncrasies between vendor's implementations, namely to do with auto-vectorization. AMD's compiler doesn't auto-vectorize, and nVidia's Fermi/Kepler hardware is scalar, so you end up having to write multiple code-paths for each architecture anyway to get best performance. All of the companies use highly-patched versions of Clang/LLVM for their OpenCL compiler, and they're only now starting to standardize on features, releasing them into the mainline, so this situation should improve with time.

Longer term, OpenCL is pretty promising for portable heterogeneous high-performance computing. In addition to GPUs, the compute kernels can run on CPU cores in parallel and there are a few companies writing implementations for their FPGA hardware too, and it'll be able to support future unified CPU/GPU memory addressing models. Intel is also heavily invested into OpenCL adoption for it's hardware.

Re:Hardware Requirement: 24 GB RAM (1)

dj_tla (1048764) | about 2 years ago | (#42148367)

That's interesting... we are looking to interface with FPGA hardware too for some things, so a heterogeneous implementation would be great. I'll keep checking in on OpenCL as time goes on. Thanks!

Destination: Void (1)

ThatsNotPudding (1045640) | about 2 years ago | (#42145339)

Destination: Void is a great Frank Herbert book along these lines; always thought it would make a great play. Admittedly, the last line is a bit too cheesy, though.

Size of model too small still (0)

Anonymous Coward | about 2 years ago | (#42147091)

large scale is a bit of a joke, it's like describing an amoeba as a large scale creature because it's large scale compared to a protein. A four year old and write numbers, and do loads of other things besides. I suspect a computational model would need more processing power than the world can put together.

understanding the brain (2)

gordona (121157) | about 2 years ago | (#42147261)

If the brain were simple enough to be understood, it would be too simple to understand itself. (anonymous author).

Re:understanding the brain (2)

ceoyoyo (59147) | about 2 years ago | (#42149537)

That stupid quote has always bothered me. "Understanding" doesn't mean knowledge of every feature to an arbitrary level of detail. I understand the basic functioning of my couch even though it contains more particles than my brain so my brain cannot possibly contain arbitrarily detailed knowledge of it.

Re:understanding the brain (1)

HybridST (894157) | about 2 years ago | (#42150199)

Neither correctly recalled nor attributed but that's not an issue in these days so don't worry too much about it.

"If the brain were so simple we could understand it, we would be so simple we couldn't."
Lyall Watson

I started typing and Google showed me the way.

On a somewhat related note although Bing is improving I hope it never becomes a verb...

Re:understanding the brain (1)

VortexCortex (1117377) | about 2 years ago | (#42151447)

If the brain were simple enough to be understood, it would be too simple to understand itself. (anonymous author).

Which is why we just build bigger brains. o_O

2.5 million vs 100 billion (0)

Anonymous Coward | about 2 years ago | (#42151045)

The paper abstract says 2.5 million neurons are simulated in Spaun, at 1/3600 speed. A human brain has 100 billion. So I guess it's off by a factor of 144,000,000 from doing my homework for me.

Goodbye anti-spam automated challenge systems (1)

Raystonn (1463901) | about 2 years ago | (#42152719)

Think how much the spammers and data miners would pay for such a simulated brain. Typical anti-spammer challenges on the web involve presentation of a picture of a sequence of characters and digits, which you must identify and repeat back as ASCII text. This simulated brain could easily accomplish that task. What challenge system will we switch to next...

Re:Goodbye anti-spam automated challenge systems (1)

leonem (700464) | about 2 years ago | (#42154445)

Greg Egan describes a world in http://en.wikipedia.org/wiki/Permutation_City [wikipedia.org] where the spam arms race has led to intelligent spam bots, and spam filters which are a simplified simulation of your own brain, which reads the spam to decide if you would want to see it yourself.

(N.B. I wouldn't want to give the impression that's all there is to the book, it's just a very, very small part of it. It's a good read if you think you'd like a novel which explores some of the implications of simulating human brains. The simulation speed is an issue too: if you want to go talk with the AIs you either have to do it 'by post' or slow your own brain down to their speed.)

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>