Silicon Brain: 1,000,000 ARM cores - Computerphile

The Human Brain Project is behind this attempt to build a million core brain simulator. Professor Steve Furber of the University of Manchester & one of the pioneers behind the original ARM chip, takes us through the SpiNNaker Project.
How Computer Memory Works: kzbin.info/www/bejne/jna3i6KIjsmnodk
Don Knuth on Email: kzbin.info/www/bejne/h4SboqqDo8ZrldE
Brian Kerninghan on Bell Labs: kzbin.info/www/bejne/h3euZ4V9aZyVrdk
"C" Programming Language: Brian Kernighan: kzbin.info/www/bejne/mpaVeaasrcaZbq8
Steve Furber on BBC Micro: kzbin.info/www/bejne/r2W6eGhqbs5mj7s
Machine Learning: COMING SOON
For more information on the Human Brain Project: bit.ly/computerphileHBP
computerphile
computer_phile
This video was filmed and edited by Sean Riley.
Computer Science at the University of Nottingham: bit.ly/nottscomputer
Computerphile is a sister project to Brady Haran's Numberphile. More at www.bradyharan.com

[@mrprototype438]

"It seems biology has found a way to distribute information so that if you lose small components, you don't lose the memory" An acronym must be produced for this, it is IT law. I suggest; R.A.I.N (redundant array of independent neurons) ©2015 My guess is that the brain uses a RAIN 6 configuration.

[@jettanderson9828]

Sorry to be offtopic but does any of you know a way to get back into an Instagram account? I somehow lost the account password. I love any help you can give me

[@jettanderson9828]

@Ryder Shane thanks so much for your reply. I got to the site through google and I'm trying it out now. Seems to take quite some time so I will reply here later with my results.

[@utubekullanicisi]

@Ben Cameron It's a bot comment. They're advertizing their Instagram account recovery service that is a fraud.

[@Irnerio21]

Wow! This is actually a ComputerPile

[@JohnMiller-mmuldoor]

🥁 da dum tsk

[@CompanionCube]

in 2065 we'll laugh at how these computers were big as rooms in 2015 just like we now in 2015 laugh about how computer were big as rooms in 1965

[@Timon-IrishFolk]

probably not, cause that would violate moores law. But we will laugh how primitiv we programmed

[@RSK412]

We will laugh about the clunky power sources and processor inefficiencies.

[@firstnamelastname4752]

We'll laugh at how we used to type with keyboards.

[@keineahnungnet]

The question is, will we laugh in 2065 or has the humanity destroyed itself by then? :D

[@doppelrutsch9540]

ben3847 Or maybe we'll be so advanced that we don't laugh at something unfunny that we really couldn't help.

[@EugeneKhutoryansky]

That sounds like an amazing project. It is hard to believe that they will be able to simulate the number of nerve cells inside a mouse brain. Though, the question I have is, how fast will the simulation be, compared to the real life processing speed of an actual mouse brain?

[@asdf30111]

+Eugene Khutoryansky Should be about 1,000,000 times faster. A day for such a being would be like 2,000 years that why people say once we build human level brain inside a computer it will advance so fast. (not that we yet fully coded a mouse brain, but if we did it should be alive). If we tried even "now" we can build a computer by 2020s that can store the whole human brain, but it will be useless till we code one. That is why people say we should have human level ai by 2030s-2040s.

[@Skyler827]

Eugene Khutoryansky They are still working on it, but he said they will eventually get it up to real time speed of a mouse brain.

[@UnluckyFatGuy]

+Eugene Khutoryansky @5:55 he said they were aiming for real time processing. So it sounds like they're trying to get it up to the speed of a mouse brain

[@hellterminator]

+Jan Švejda That would be true if they were going with 1 processor = 1 neuron but the video clearly states they're aiming for 1 processor = 1000 neurons. It is also stated their goal is real time simulation, not 1000 times sped up.

[@PutItAway101]

+asdf30111 "Human level" intelligence has been "ten to twenty years away" since the 1940s.

[@red_isopat]

now, add 99 million more

[@DustinRodriguez1_0]

There was an experiment a year or so ago (maybe two) which connected the brains of two mice. They even did it over a network, such that impulses from one brain were picked up by a sensor and conveyed to the brain of a different mouse. I want to see a similar approach taken, except connect a mouse brain to one of the SpiNNaker boards. Start with a 'blank' network in the board, and connect the mouses brain to it - preferrably from many points on the mouse brain, and starting with the youngest mouse possible. I would also like to see more videos about this project, concentrating more on the software than the hardware aspect. How do they encode the neural network? For the event-driven architecture on each core, did they develop a low-level system or are they using maybe a stripped down existing kernel (maybe one of the academic kernels with proven correctness?)?

[@johanlarsson9805]

I have been doing this and thinking about these things for 7 years now, and his machine make me so envious. I think that event driven is the way to go when simulating a "brain" or consciousness, looking forward to hearing more about this in the future.

[@rickyoswald]

Has the PHD student not heard of cable management?

[@rehmsmeyer]

+Ricky Oswald watch?v=FY1XB0rrYes

[@einball]

+Ricky Oswald The problem is the toroidal network shape you need to wire those into. That defeats any cable management which is awesome for cartesian, star networked and even hypercubical network topologies but not for the toroidal shaped network :)

[@MeepChangeling]

+Haniff Din Oh yes because astetics is what's important with an experimental computer system, not it's functionality. Save the tarting up of machines for consumer grade tat.

[@SerBallister]

+Ricky Oswald It's a prototype, I'd imagine it gets re-assembled so often that it's not worth organising and dismantling the cabling all the time.

[@MePeterNicholls]

+PicknPlaceDIY all connections go to hubs and are very likely to have redundancy too, so probably not important in the test machine. I assume the final system will be more managed

[@gwenynorisu6883]

Anyway, imagine going back in time and showing the plans to someone in the 1960s. "These ten racks, in the future, won't just house one central processor, but _a million."_

[@djvar94]

I'm sad to not see professor Steve Furber around this channel anymore :'( please bring him back, he is one of my favourites!!!

[@tatianatub]

its 1,000,000 you forgot a comma

[@AndyIvan74]

Thanks Captain Grammar Man! The world is a better place now.

[@tommihommi1]

ashley beaumont according to ISO, dots or spaces should be used. Comma is for the decimal point

[@JBinero]

ashley beaumont In most of the world, that number is equal to 1. :P

[@jordanchen99]

He says a hundred thousand in the video so I guessing he added an extra 0

[@tommihommi1]

Jordan Chen The final System will have a million cores, the first part that's already finished only has something over a hundred thousand

[@Kee-Lo]

Wow this is amazing, I wish you the very best with this project Prof. Steve Furber.

[@mjallan123]

Imagine the amount of power needed for all the processors to potentially simulate 1% of the human brain! Our brains run at 100% and only need an apple and a coffee in the morning to function xD

[@MuffinTastic]

liquidminds of course our brains run at 100%, otherwise evolution would have taken the unnecessary lumps away and we'd end up with a drastically smaller brain

[@MigranBTW]

liquidminds That's because brains don't work that way. If you would be using 100% of your muscles at once, it would be pretty hard to move right? Same with brains.

[@Clairvoire]

MuffinTastic we use 100% of it, but it doesn't run at 100%. In fact, synapses need to rest between firings, which is why using the same pathways becomes harder and harder if we stress them (saying the same word over and over for instance makes it sound like nonsense) The condition where far too many synapses fire is a seizure.

[@SciStone]

+liquidminds [citation needed]

[@superliro100]

+zedo28 if you are angry all your muscles are umder stress

[@Kram1032]

Million cores = 1% of human brain? All things considered, two more orders of magnitude (or like 7 if we go in factors of 2) isn't _that_ far off anymore. The only problem is the overall size of the machine in question. But given that a large portion of our brain is made for navigating the world, perhaps that much isn't even necessary to mimic cognitive capabilities of humans.

[@Clairvoire]

Kram1032 I agree, so much brain is dedicated to locomotion, that brain:mass ratio seems more important than just brain size when it comes to intelligence. Once we figure out in what ways our brain is un-efficient, we'll be able to cut out those portions and get to far smaller scales

[@Kram1032]

***** Yes, that's equivalent to "Million cores = 1% of human brain" - they are a factor of 100 or 2 orders of magnitude away from that.

[@puppeli]

+Joe Mills i thought they said that their *goal* is to model 1000 neurons on each core, once they have optimized the software that is. Right now their algorithms can only manage something like 200 neurons per core.. if i remember correctly (i have bad memory, and im too lazy to double check :P)

[@Kram1032]

Graphene based computing is progressing at a nice rate. We'll see about that. A sufficiently large computer could _already_ do it (although we still need more accurate models). it just wouldn't be particularly affordable.

[@FragMentEditing]

The "soul" is not real. The brain is the source of everything about you. It IS you, it is your personality, it is your memories, it is your creativity, everything. Please stay away from science videos if you're gonna talk nonsense.

[@MrBoobcube]

i love what you guys are doing. it is very difficult, but also very useful. cheers.

[@Cheefoo124]

Wait, did he just say the human brain is roughly 1000 mouse brains? I guess I'm okay with that.

[@kindpotato]

Yes a house mouse has about 70 million neurons. But we have something like 80 billion. So that's a little more than a thousand but yeah.

[@tommylyb]

To Coop772: I'm an european engineer working at an American chemical company. Yes, I'm used to indicate pipe diameters in inches because of the ANSI standard we use. Because of this I really think in inches when talking about pipe sizing (everybody in our company does). However, wall thickness is back in mm again and lengths in meters.

[@MePeterNicholls]

Thank you for these videos. I'd have no access to all this otherwise! Amazing stuff

[@SciStone]

PLEASE more on this!

[@Azivegu]

+Computerphile, would it be possible to make a video about what this computer can do and how it does it? I feel you only hinted at what it is capable of and this is just so fantastically incredible (for now) that it deserves more attention. The fact that we are up to 10 mouse brains is for me quit an achievement.

[@asdf30111]

+Azivegu It simulates a brain. However while it can simulate a mouse brain that does it mean it will you still need to "code" it in. Now if you do code it in it will be some what aware but not living (I always hated the scientific definition of living far to narrow). Of course their is a problem of feeding the computer data other wise the mouse will be blind deaf ect and for that you need to read real world data from real would mice. If any thing the outside will be harder to code then the inside (good thing humans do not need too much more data then mice) but once coded it will be easier to scale up then the brain. "outside">mouse brain Human brain>"outside"

[@FredGandt]

On Sunday, ***** posted about brains made of skin, now this about brains made of ARMs! The internet is a scary freak show.

[@MarkBruce]

More so every year!

[@DustinRodriguez1_0]

+Fred Gandt The Internet is reality. Reality is a scary freak show. Which is amazing and beautiful!

[@xanokothe]

Finally a very interesting video here. Thank you

[@gabrielbrunheira]

Amazing project! I wonder why they didn't use FPGA's instead. Looks like positive impact on both design process and final processing capabilities to me.

[@tutacat]

Way less efficient

[@dannygjk]

A spinnaker is also a sail hence the image shown when he starts his description of the project.

[@telesniper2]

"If you were plowing a field, which would you rather use? Two strong oxen or 1024 chickens?" -Seymour Cray

[@ShaunCullen]

That was a super interesting video thanks!

[@Methylenedream]

0:23 I take personal offense to that. My brain is the equivalent of AT LEAST an even dozen mouse brains!

[@thealternativej7994]

lol

[@CookingWithCows]

so what you're saying is that your brain is at least a slight bit more than 1% of a normal human brain? I guess that's technically correct, even if your brain is a normal human brain.

[@pattikillem666]

I wish this video was 18 hours. Detailed content about this project, it's so fucking interesting.

[@davidellis4031]

Coop772: (sorry, for some reason I can't reply directly to your question) Here in the UK, we have a particularly strange mix of units. Feet/inches/pounds etc. are called imperial measurements, I think because of long disappeared British empire, but we increasingly use metric. I know for sure the metric system comes from France. It's now even become illegal to only display imperial values at shops as we try to standardise with the rest of the European union - a bit over the top but lets face it if you put what you know and love aside it does make more sense when everything is more and more computerised. Units that go up to 12 or 16 can make perfect sense when you do mental maths however. Now, schools teach pretty much only metric, apart from miles - that's still a standard measurement. Speed limits and distances are all in miles. Every car I've had, including German ones and Toyotas built both here and in France, all are fitted standard with a mph speedo, and measure fuel consumption in mpg. I guess if we started measuring in kilometres per litre, with our high petrol prices, we would all die of dehydration from non-stop crying. I would however prefer to be able to speed along at 100km/hr rather than the pedestrian 62mph, even though they are the same! So you end up with older people still using pounds and inches, but more and more, especially for units that you directly experience yourself - the weight of your luggage, the length of your toothbrush, etc. metric is taking over. But of course there are always exceptions, the one I can think of is floorspace because it sounds bigger in square feet. My house is leet square feet (really - the builders plans say 1337 sq ft), but in meters it would only be 130. Hope this helps if you ever read it!

[@teknoman117]

Obviously they must have started this project quite some time ago, but what i'd be interested in is seeing a large cluster computer built around the IBM SyNAPSE chip, which has one million neurons and 256 million synapses implemented in hardware on a single chip.

[@adryncharn1910]

This is really cool!

[@parody4042]

I had a brief but good chat with him at cafescientifique on the subjuct id love to get in volved in this project more

[@mateja176]

Outstanding! I'd love to be able to contribute to the project.

[@morezco]

did he say we lose a neuron every second? for real? I'm scared af now man

[@BunnyFett]

Holy moly, this is gorgeous. This makes me soo giddy!

[@imir8atu744]

just cool, when is it going to be completed?

[@R3Cat]

To the coop772 guy: Yes we use both meters and feet and inches. We use the unit that is most similar. Like how your pinky is like a centimeter wide, but your knuckles are an inch long. Much better than saying a pinky is 1/3rd of an inch or that your knuckles are 3 centimeters

[@dylandailey3191]

In 40 years we'll be commenting on how ridiculously large of a machine we needed to simulate a brain, same as we are surprised at the size of currently 40 yr old calculator. Technology is great.

[@ShahrukHossain]

An update on this project is mandatory now that the million mark has been acheived !

[@paxdriver]

1965 they weren't measuring transistors in nanometers, they can't scale down infinitely, hence the need for multiple cores, hyperthreading and bus speeds. My prediction would be that they'll need supercomputers to efficiently hard code these multicored super comps and we'll go back to algorithms making things faster rather than processing. The brain works because of its ability to rearrange itself on the fly

[@AndyPayne42]

Memory doesnt get deleted like that because hundreds of neurons dont store a memory but its the symphony of millions of neurons firing. in a rhythm We are so far away - its like we are playing w mud still trying to make transistor. We need to be studying the nonlinear equations that govern the neuron and their dependence on the array of receptors at the connections. Once we know more about that then we can apply it to the latest array of processors.

[@gameworkerty]

I'm actually floored that it only takes a million to get to 1%. Only 100 million to emulate (theoretically) a human brain! Amazing.

[@gameworkerty]

+Haniff Din its not obvious, please explain. I don't mean that it will be a working human brain.

[@gameworkerty]

+Haniff Din did you watch the video? he said that per each of those million cores there would be 1000 simulated neurons. so a million is a billion neurons, 100 million is 100 billion neurons, roughly in the ballpark of the 300 billion figure. or are you saying that it is obvious that the presenter is wrong about his 1% figure?

[@pjousma]

Those circuit boards look awesome.

[@Velo1010]

Fascinating. When comparing the human brain to a computer you can see some similarities. For starters we look at memory. Computers have long term, short term, and permanent memory. Humans brains have similar characteristics.

[@hardrocklobsterroll395]

Can someone explain the toroidal hexagon signaling arrangement? I’m having trouble understanding what it would look like. (I have some experience with hardware signaling, timing, and addressing so it’s not quite necessary to ELI5)

[@richbuilds_com]

He's such an eloquent speaker :-)

[@michaelbyrne8238]

What are the properties of each of the million neurons and what are the connections between them? An Aplysia feeding network can be described by a dozen neurons but they are all different and inhibit or excite each other in specific ways.

[@slap_my_hand]

If you would just simulate a simple network, and add some I/O, could the network "learn" a few things, if you would run it long enough? There are some programms, which can learn some games like platformers or racing games, but i think it would be much harder for a virtual network to learn how to decode something like a video signal.

[@djole94hns]

It's OVER 9000 ARM CORES! (I am very, very sorry. I just had to.)

[@asdf30111]

+Albert Rashica Nope way under 9000 factorial. 1000000=/=80995899866871908582913120800979496475828146392946408922219130690909015407353605447575041936572856149436036552693202056107438918510666946549242001162011108501701783175388347818676665807750253993451959460728919143729422035131295720201773066711254876977130397164271629343887027389990484870424761985903139252132590695173046063988540822033659291766968548601878973082087324902401031256293072745024794472029386569310777454039154913625335976240736527174750248807592665967609235867427486687394624065354208222807571075334926662512401020728627137483474443097491765137643325508329100387102323595906471784431277794544091057622014418785718517874052992723535625962533773077786483156733351003985015312850063097297688383104165944922291877154827827387776783098860019115057271734623090315061207654176768334046942312777866852067403680706678717220065935289287403445179487704221022864747118318894667734215824448325304218344022286776464088159484417296105456598516624413422536284583776565645291607236937428081090821806793544279120012808130282214882523710762422258364719739866816333989515845762465054392937290504744951946352879274545232972564908356550783239691860815473962907109723178881997716171297160533116698713610391919943326824062223086833799317518486256170015876743951750313950982026682426542544094208626893368737023171753939606048266880220310852090313669977486987472993944815087101684853278969509545919549706207250476276826257482834355079375617595073690586658619701622055622829408511142193149219321202115385445141995097765323352682497411627849615546692628100061453783287243728334083773879921864420021284893537157101013755797314370325600492358512136266873444682950591827219914972688105498476577594993655491030248845071787094361839130685085895669277350919528519040839999868357050098337385927373281375263237042537200753320301144296397290856074160598702489252961353923612414891351582623280096520530805015187345480542343562496692698492694214185299818736433742085638672673329050467140134713134468413594627818455997427796579861980614609578207714757038352462441858241710655713910919817661137504413472003942614063293534136276732154777280725072555387214225458814560612490917195819468723492949949608592360201904332140376342803298648755021691459703203499071419672288210791510158647945293799041537077117640788722848964195451243230908778508479867559971743934831811057793800314206457521004503213629429497616220334139654359342451549062125299397872906187588176978167460543617705382392994470921463264827844533115902495233234150851557657597791355044387227684622680674494805121951133025107233859851779656815997145907995528620829496378409568948397966974398491052255019449002246193926860608063369359872606288223035513221539114085007169426591775298089086124125093952209885783195418110028923735717150890469150784357724104644776964910677679883242533677938316389410973732395444201079750212120550616345037817772019356650391444847620711299754242383055864220480828185182968042179574353080017192021929028380499662521541596824332934347763628432269660483748887156747338323191578608851821333768867964318876272281007423156167637967305326584166406326581509780957028867932012535128034477273156952884437978896498272926912255085259131098903579582431573260491240198629897044711201325353375752517847165346469983567245747234544572853913624415076812082116146062304579842385737902668727513869592130204810729781447544551016621846145831875160596451952559921744089381286482764414313934198060851617383876559559283469286358361658866503058426656733327419897606473677142188525420552368639731551738356813994608548743926660874407892744207434385685338091740680604162598145801189637540344148271338799929922762423236774236214757770425272691915915339149187596426462764984872474774665067725463397284291584565589138210009405665681920188323186473860405898308222499661520559037262049669645313468190053589630048048190811685333651521436804712220924826856416074488448417055779348315541986500412665196677314851189969015948220300920319322560849352306930367659309862133233368690766759515197579131662716879086665669656878734267138132322839517024317655413573019441790702086958908773081191753912029344110682744511618213853915085135205725512549523020741529779310101435095641952249655159793988276929724042596481940887778147926719038243012576420565706448609533230616094368592246349710411125705209009709373018604507452956279574966424952118320346345475240913103968988847896096522843012431757371198194159304655060189335334070878621886833481355553069375675772881642866354771213339862614020224667652363283573131757734767613223139581029923644849997150345295511037746012892963433064897706296823643603966666401767120397697949140221534287489931325379441054292902055801262918153399954985564623219002596405504258481540827164943397104973068050806801745187128308814119331746084033661493403193411069342966314725885275971704708684878518343017262295278765362109587118084252805463618778863285828189508298848574477995589935325649661422793992584465345641338612580959522983043885990517651996945544381621055050069740655173241823410248247089728707428342700298987136158026413162684315079956050110462918217198764312889367739992323922946383673935187707357694190670826385032014209204434365787459432490859680189754189602646098160968399054298991477668683246300599818941541417719370570725384530199348976527708522067483481324188727699921439331094829103518787037607667875717572627959428680905764345570248508730535699380567093887156513763033363760063908701615609744861406276947749026653563959292876843156065612281239990643934684266221998644247380938524538853665110382348281416184858923905574219464635738390799351896374953686200239306956024060374456834280240227813134402649150402647927883728115141310219650044756673072056719124955472784888958769076142879024091072790868410244349257862137143268818996631138599981891775276256046816038131677075041353397958374445708140565105056364093222825996579850203332604148071579889388169126839344034680169273512150891930837246322023509463915000641274514379421278744160532721183807498479073947744671645683266299328557082077341580845446412951403311504381585926361653545319757185057800983106523315562127935784750538589104469168784601719643894876629731584643329846353549226171791375124980021877770074576007319522647384409670110730004751808547879808812783078157174033294272954296048340312922422355059255886643750420008098956297512735175019419406453125089642046320670503848060523922366566417606417635227000454140222483216986178005164786681524168092438655976092623180598580453389368893634888275173836608117293042890516061723476136682713976032463129864551072345844225074482319297026518389761580046154517762058635776121328900189084369572023938967470693766053378469225663965288409027465833554818736253609638553798008715932900652926773110791215030582813897726752559345930529075162013520019553157416862663637957536165242823520760163331353836603324565329007170980066658832149187213866671200915863332450115225925776657876407376874111231774400385139856819254748100808423031261130694204339259075950783228512563080177267984686824807695035599035949897729917446569938017862710061560015565747727138820973377694916834717751236216748276466064371482150498198384755481494077267455986149561337562536110700915451197536826478360906232635355321279845527509268027935773937754290135387043083966404156395935438612635985311895272558767236144945060004118597044863726465568117296501598026190799163615373887993978915265323602488211196521990175860946532390167678255453359289071690628837211057658405938566939525213799294496386784162371304211175157334382585004669601908847779268042193597677532426912392980054248592496996034372207119229964170245591604058671388240706332871086973564521142388237010544085875658348059852673236755447095733493162736319409814699762787567688990770652517290197745065475201543508109559327229366534266752065470274074136242586843104334416000629690697765150040836926552164847455406144811985599565502550770745585114511442400060230545208833330338414025120778511493362288467033685674079431417505677308118218699678216535045644879288422888133801794987771650230245677092048379930362917495546965415927578217205118980437221400869059069292242253380471883028866778410747494798287178055981350197078503759028846060964731733269106414408516633206309324308974042650836595410504873700815739165896648275291164237075591475505351096401784554794177003312298262210734172999303212111868405689356606236665789731380233187450447601923200940245867350452740262838226225190609820370295788211322649123632462359775423525028342212685065285340677150775975377535304193511467433642558051880721509903551734918770437290423459575630691458246753053781911920213781359269701054911306805154555900110922082560240552383462997091581344071371898945124579942890212884157480690030608642412718553663621166984809943416377760511277293309266002660920057986812713834286105917906994123454136282734575491331466398376149339687256067046211693583365139566277078465590974831719008922346550832203625018027677384881550812616859062557602326876917007295837285395958659564619648643660886787568897935260714149576409396123568466159638189106586294698441834959178055129829400023175831131347353301975159162607430388944265333957320008763399315833813204072398219624784292760029884336986083765718974599868588369803958250722941186200927629068533131206606358516915575946151796114755839515090008583053127275522960856309803710435391532659761148159056063737415313447223692618481755226741965806404046000911890471687770819818468191498963275597290918829946587949800743233782182182556250065144124162621892548638539612876876425925841525371502637320195203406267163888251635748130237367760046378885368762931869674463997850693710827301611877816963268156023896329548782009213418125167213668956004798192602829289267120309078506293701360713639694356397970443891477202000065327547088106117171866175277040421792053836288865202893702267617413504651510848910218599110960388486480603517258173099330848356166056516860834500534451784022576183206940041562680089775154738867622275782949977333964057035233273148666736192016502912107750891881151747059755151993684625597496577921240157713136835727546099089944716848099007295500578714682150942901714159805821406864874203447416412681777739358535853527875825309229566250257667955302201983151221532574450842355791762406003917018839235999657213160237754760857320561333078124297455062471230870123603895511658597860220107088607380690098026462334689052518447029630721094303152541676708997933174882317048857557495826120208075452995084327396385788621644912374918486175184067237681668287409050135827377079219491266375203267845680948315203125590359146840513193078632412843726536584781532470970656990505794445049905931139138916217023503993640870103337134068016438153117613506476303352214064255496910437370439228060259178037024870993838784107706934999858987737080215152170616869684071324880061132910867484881797085770792410531026391550101895692397101928349258522761006768378989725933948218570020038321179423692220492032924575092980029722461326705715404749717488681851503668202220228273927614777274484801139038234522503115605382377649954863459965735478722181901735578547755352490914177712837059457453571258027336824888929960439404420668452284878598445254315869077512744393890597704612987062693414731021343714767403380941896805543372512313591139343776432010610497226906037724509120972231127804002797674446851465568630558410597330640057252691896186026261372371628896714586703385756534733351362186255943628533030491347718348504186536456481471207708310664947697531287427343080963931357509034111650275232200852217008979534731636077664377110289829441711466227021896556900992544266229384776880877690942035060117292124693866548241632664116103079322389360850404125785069761542805358717895427500321437937561376241134312686938080493845008829461761260111944021901067865127066244297106277092180176286163870917232679891849789919224776382384279833849832108774333828739160480175377444282699342374515982022335455027147895251580706545221117894754699731167714219212146408681740052959394566458797358853472698744520128566508860750610935278251522532047874155198901323121922891237290999372509866276770027981774883231164230423345464663567674980291560408652880189984809686833939161951539414003453181863475860736690047200410075939379741152172877937530612666263481090346788490958710305326985891224610543282442007205304115834373897702056477494072978701592758088865272323270693710043929261987286205229708656798046438526139369000584037677144735868059827919010950953286543578066982180341243036239225638590222646915117117500219304788408413816562993828341715402938666161376717174931182410366777992508252197931414592154229297376595917455221687735417045558287448262810657655247244484525487670066452384970999937556026798335137628332500081452843987635650896274853828076474803033985532483433741306270227301647626462259648745670947705094330378821878014378477427373076700354852628353629917071500731824763202673044581707682098704926240172777916575288679053399001108483169215447580559699608068918020296343250819473760592708800863597466070131968874567880823463858291061018362945721407833214509679292680683927339570367843534933183413020808328250705498724572233896811503136294324334052792391165788454756253345011912690872921844103831146274404747174996164232922256362566373543561203433566781685462794332571008331493075216410853619359072806746405326360310961687835222868039489710881549847129803918952593771971896714340931616416563720277470576828940766223128047287217679021183488834507985521002618529298366550521506217989048217642343506145830106940954017690468720883313155585528739558526815139310026984347617023729949907471351245199190241376802368802742384124086158699577559134590888314977203443955835603273943058765640224911822486562367827633964040071784306268005019351190832544899043935115055765493669151526293543967908941211232083927239604755910947147063630967056725487296515818299835437676280383008078486174357763781308262013652029721934980264275068211763398576840855197039061902363015569806419850832552350144175978618970845583646507774830371949150787558228368502266174221009019874848145621038008598162202417983596588261843283963124411695644847320018084743277574108331811499691759980740218833736005204926416708949426012995932491933828640142469956165371990007502466747270540457455775254689776897736378585490606385544843290372661782899604679811229129832611137224809177509429414080719942563838578160615303346220553002342645598059977329894736963545137735125428964483303359959524758289686407076677287667640704499380942171489839122034100098766522186603202055844530847365602392304475568983534926434611327246901178884223039853891163657974972598801096740669571691942355687105913695888962580538509379019568538663341258126906909984024285428922841196578267684570612831089471505825524577528465017015416957102789111345599188250466339269927205106572426369486409171307809172426469301776547742901504161687867307368243441541879142042327682978277800389906869805685770611546102868668794076019664015702988088414936473644747972684807498413164917655553262555254207583876428237716878354138096923833219898615902145217817699507428997526285568032225979060352809858934979575767435994094629510455429827771642340538855765463682140289281659142146686698170562804795809935379108838325846804250763105862252824948088931159856559258610906279697124987095829093899303904797182231909681582091505012348133921681646966460348990851339271512857853555837870424753833891673147582452941710628390729426741414314931395304789194663736353182735505409868130753982454765765613137792268028209143157440351476185093550271388575667085146802690367531995204611367052208861680241242289488382941197630741418585826977847648415085214939508523736053085522724819697926604698487228815579917248280979839691009766389537346456396178589751288670478642533543863646526413893452037048840616107828591431962282923159645380735652513568233012717471754135113548940916072362670264986312696062073412890871958328554768867228804740068895266045349592627483626258198924026163471297673944692745012306008754275588742386636249538122730161407934276223830865305555312683060888380285872123148543105968509487333010981556212691023978814099862293511102310644654674394726676741840847517193237727304854036176064969472651717133819141422615123864096222178634794025442830752281186706552456328194709589639285571800945562842374767823098005512335475327602356139893723967187034259395238106296510821219491764222334872591471554122146839665397259110858861359279248235669995262486260031548802306328569818644330938786135121425914174041192326088209237671710652793570885731443937193990643491846638983687008614632777929505075291973608553615956903154433177260694557985425422305326257613705839911225371135522011972370497695429522913381279102414505482524232868473480771665768958644808837687667856584123066496508283943133509397378630140384238859521121872390280876636289838192555454442254878889317758729312798858649534559818165629785484744048986111278327783510300522791315963838543155940586927117110400809804956374014351307721770429578248771726157123072638420888204713576691009299417916314134788884611996068834014465701954706671890624827878374220206530266136568381705718981352106013155976392846202033999011840082783221229359344139256842960269192400288754439431595025984285725822567339451752529042885573271007913181198980058908588133525033298710945616112485263231455145338638064849928346075947114315491594617525580573563401981581595952023470182427073448858419812511008532275330332848878588506502878939168098911228525465188708184532914395179478471157605916529778031902971652399700593053134673097883487578399956314528466983016327112592296108560676175557595339845290469765977986050170522530454894780525822052298503491685520738897252241310411400694188493702640634540998121201910366489995592345766425800532682660001013132102833167656808958410994935348309392529230476614206890334854816579080871339690768249830705929962077885475493068450271649048827151170680987496647204092264142990545863266415848775864100230680336626986288829328819238525102217537867959521749802546436024248923856098794665004285720797018376096640618621942243326611303302932276004418770923304025155334315820831945999531701325164320919002373935285722350655123310389798679498703727812766344202745770810776973131875295485429865522517977791723294512040533554781209305196082254165373354635528402434401944348590049843340983247821577502494539960380035141614015068952685797440191758622035106742403977549083255175100746286233782163629445320560487605676726035077629632387872942704432908874386390621625162133416441292348604014152129857924148541586712198510994493644558437465573660078419206107492526640621669186942686545706833390212685666591029003176412290334102605355751226658431097396621022719893559657303069726176647870223127976931805287788662252216041764401735275828920663579257155872842430898800288256467360368665358336243765341334707249756288756980815431504904494665029957736322599219761996085503995800150446857758762417462818205693361332011927948605439407376544936559323823188673115989372467946797338563598781147502347730221985953476234060061460034009736867081071306981844859524931049824293219544084758764654961311856784015555560158315492869839268896008392638630823604155564048806213857620052497546215087586222163898563112384498342709746239985273451625254676371442662666797640839054989046359119650900565379432676881379610789135675024909013422672900886366375069033126017484851211006681515286159606580747399449674519251310053826389465516009068360517967967752848280274822430415125175158077614742383174425349746615742676968041155615259625206057351442736431365978711636395852124592875920294619768953406157324682102369278310062779582169437451074379287665415867368158317819792050658200062065381513015926564968926784566060838212740733039879862411474886157071618895403470911128001246853741676530554373470374678712804967616627239013887375811255271248214720973548311192778688271626291621278323136827062890101119542829934399687179273395553505989116137057592693090873002244524774893837991592262959351422999554790947966136578138495980250007483252269813943556451966864055051816557825013871104362821126646334075350374437314482960421227561494245970005956984459286141981057994809087024360976662383664505734208796034121749117313340718284175405413718008151975103725091227756391945375501944923488813180783113738470791452533983158196971425073139609139317598712229924443826435749855454565924576788156157568215362102475650036742278016367059789602026218395416110684269932428314792410398729977093074589580530274853696434326650548082743624384231846326080664583602835649618092135550645611653547161522974258620878902326453440927136236946983613424879327032568360227343079322919350241707609642788854490335597873120673761311147059787518111605820534182688354746703751637725082005817930298815360638775069305292082559715870224717812565411148357005951207661127153995923412259798914484409962610214860444983915702267464639490014600996153042625275269090607928069673850728370754197558728812466509516566436979633268006627667246159149017142663140694058904055958321611715738005545033361826657350553098262410257742255653226253939606631891780490182600276102674326902585089513405868592881390417094053145739987673001112233096761138894870807257039873026394229506543821628470253373003904928230243552507079230333200955581261603347284226473244387780467794591820256516305220839199833965606310849867046762462599479438491348665818867455713906939104848944680198584764438788361551174456060940295611283796706271042878362642279281217061574760068571469028728573550774422262442662125777900100469881719543378098216886384516114461201195094546307150074006867843517239262359172050584632819429230939378125623136237497006408854804425100205300028155318414055586630135025074746289797386196735987159940345920815817930351532046284026376194644087152202480078433513975445465973986092216735371898556834120460217904438922931359040579880396358249581435187824266229467640581336876847039479499511775100191696259592479453845241774405899940594958426736121158265305205240901613982192938132164623363752383706012067998446258469802958144795625466443657884528110690619442616506618613988338713955501071895728888937280531792087802981222801071099639108035347474781841090993741459837241450220966757200453637946000697631779039674641621296243504530399520930469425080255490906687359338872971502385471020453554878901870336752222825765780475442191798983327236649069382252743482174374880110633814631848487948177987609100180679769994979511994574164971629629116759563083025913477660314212068316823783643846309684489238870409976761913989906824032463763134328303097516461674725116098143610268181953267617393208411634378285179191047686553137888091296684753904742658211681866179038792833871765440058253245762867526043838399414082410733664874674555245461596269520439154824962248460613608370964339484538085492992515142750657397753763080855313235994750564136887663560563362668603330013252630012300678129464429487288990754057026491697981401486577121379471816911756065025647251111955878212234544059312167557688697927968582420471657270364722142188246660401003776056345434997164910321938001645349908593781804836112723375266929897107651529407059743788660340733809543929953684383625247440410346962162206912800879882642498361780257538453934698937359080475615894782376939927882843969210762445275248122321534639690155083592186788011757056864278669645661907649863635201822519411990500242709663592239068273293421654105033223566333985342700653004178857285971749743344487551608839352087987346461010482601275783969383590065286038168278984759404111998388791339607186614039368684319454574823052376133061142832590050733675077974330252070780105056994521031322288113378606831607347916945085371059652008863693597439893939312629193952855199008909604948872529094843907794101386784274767741585581829320160255628096431549425626509249762977005010867731063421878836134654449964878250464783313329455159179716511780740374318603338890843298838234347864902724837291245833199407873944197490419316303536892971218390915109384292569103261926769844048959243359164337417271564919004059356495016969732166377503273684238035533526467910366288812604276433729433991435584200952115982927460218369821742851123584150575586142507771791364840239039764439174011217735810549596881258056314398213080341784721301738085105033452200371560336745158388150771676472039026380483448467747665507228192582746014968326500660909946008867411119850709082325845485563887773875149225086168283076903983450708470561592421012532448431491194522858119905193301018854003194166198214532910763860900619143063034195884686969898796195237659277464298777865073590081034475357034342592000934938163739749353468237264041716373819197473012857917492516563173157691652825322319295345841508975629347394771456306377622641344165578275894563161509268803983057086202711790441318680371978843528204195364800166722535327569814589581299151259594397390315284545459148792178791708503318375411423714046302538698190322198771895356667395429885166789736068955550120989502941035179651216154772704067673772877863027555390868914634192577685567598408548579896211077434630689462076607444886345014056435604731567826105253902399494497988019997788880129950336859964174391243928666544907475193308554618542859261292867400134177918261684644729485057820486131733476754785922503730935550294579784789001482880351270682337111873210116045992972533792132108057919164920182694600505081697999186991534891103530068952376499244887814107212140789768089082644305844698893853144052915970578975107401413475912213102566275397716535968812920207795680520124877985793112512656811095889157738486694184265486083083854988501855703326371741330889176944541600810193065014084394068487333594970125998541753174244213684309065464917895861634806706925392699419145146015893569221383816606144822560445581392091757611288472431171653287718353960101761350945843524569561836461908754840284213040929367265016249092746107370702159235092448905250964094917114813554335972975749817812306960559148416028506171177477131566520478115641801408845671109008667317557259705160135144030914466333655477127469357158561401154761644575711949654628409243114217454951990569886766915510224725913106481719022693455862112643042146399158828303153743218178078052873094839018090406579702132526607208967105316623971322985546399160960340359885497772647942869447389129932551811360169150866994483966383926596383040241176516757449563044002830506325110679412069821120778072826547167746183004836679167946044860469753931426721195653817833385304364048773459187412746958863568163430252192533204639481333607563640883008954563772872905257234904512222540650332901526567254222239066048737871914094919618843514151139826658368775483069744971196463324378323126578604767586582431616926097023721183464786665504295668485490311488484232862025323664443613981488989720350137022967650460632473459182754109801617923731719585399644828450416986404078254316927471480339759176565754407829045156677545114211743399043637795332332408743720618982823931325912856046061344200019634275666741461200006044221632376295858833443846793525706306077573010896293576745062926903096076278106977890246712745449167483118232537047383337063862965387095661257223445799629893673488822367470165327156747584915485041277648783956171338156433912190874844409116076141781396965295676680505381618576384705616705955646215845843077923512864758153152854956200041158908199505491290931546309392564065320960912796839565073254732266892555293339402303771824776842822122824103880061859433304261583270626533435242929674122972963951801772234759260651099109985735480689152585747812939122741127309047501575331638984171706827339135638330086515362585532487469006047057905977943433536571538392012517108782715912602601631597741558416965327339448724698817342589867577766152670700108601401072361996062541923646798942785540085481377377921698364245545858894809286025372487576966137662667875434346370856214138334978554695057257555821674477070248719208565554328803658614533173153832029530506204524647433254655533969529792877257410349198743929755510314176024383161198275157169441100792678111496283920645900735716609979571697675174293893584904031394263689911202134227252888521338742710384332097094560649184024858059741021714418004430679870513793741649730634815700745777976721348373532076469180903498049734639340482964954071728195284611233063417347969305638351158515260569251758141384597462992351089359063408820476548868146495786628473661845197883299837426400200258713369937619612669638891760372606498061975714243061612914806793357165635436313737642687780999487830027336040659438737736080329913398425022897204748562452164943445337960751538162651294976912836229769714531372168994920425547232763037412754211523285626149052927595805060239040013317036358432754290611653065538721293553255098607183409923955775759644919188483517104612723566950829059337296631668519055418142191315537353261618695231246950133127739254327228263292963279359881919130630342701578215720177595337947515329236763028778951452487162839446395851608604286960393206190873761126712084930544442652478733906141021947337858435632138637847783360440470768717684404561362261968987065878479274601796911121497648679190733189704029865398026351809414360959087992780926224086222807556935713208125871003845842836140602498052133217924479325795224799337286507479269518280244309156227577624947958441579932036039332188624983048057250449556492575360605533960946233383754378794019988013612585267890076688418499157032960000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 In case you where wounder what calculator I used, I did not use any calculator. Not sure any calculator can even show that many digits. (No not talking about my brain, I wish) But the I can tell you the ~ amount of digits (31,681-31,719) a factorial will make and I can tell you the starting digits and the last few digits (the last few digits are easy as I am sure you see why) Do 9.5^2 -10.25 for the 1st two digits.

[@asdf30111]

DJTripleThreat78 why?... and maybe

[@felixironfist2975]

+djole94hns I know that feel, man. Sometimes the memes just wrestle control away from you. It's horrible.

[@djole94hns]

+Felix Ironfist ...Help...Me...

[@iancomtois9832]

+djole94hns "OVER 9000!" is an understatement. This is more the number of ARM cores Frieza' second form could muster. Which is a lot more. OVER 9000! is actually the bottom of the barrel in terms of DBZ power levels. But it makes a much better meme than "Super Saiyan 4."

[@martinskalvans29]

19 inches = 48.26 centimeters Subtitles with metric translation would be awesome to get immediate feel for measurements. ;)

[@maksimbanin]

Mārtiņš Kalvāns "19 inch rack" is a telecomunication enclosure standard going back to 1950s, at the very least. It's like 3 inch floppies, you shouldn't translate it, IMO.

[@superdau]

+Mārtiņš Kalvāns I'm all for metric and I really hope imperial dies soon. But in this case it's more of a name than a measurement.

[@vonantero9458]

ågosjrgåsrogjsråpgrjsoågsr

[@NavnikBHSilver]

Maksim Banin imo, the world would be a tad easier to understand and communicate with if all would just adopt the metric system.

[@MarioFanaticXV]

+Navnik BHSilver You could try learning basic multiplication and division, then you can do most of the conversions yourself.

[@TinkatheRainbowFox]

10e9 simulated real-time neurons is impressive but what is the number of connections between them? It would appear this is the limiting factor to the complexity also.

[@GalanDun]

The question is, does Arkham Knight still stutter on 100,000 ARM processors?

[@haltarys]

Can it run Crysis though ?

[@shadowtoasta]

How did they connect so many processors onto one circuit board? And does anyone know where I can learn more about comptuer hardware like that (best books? etc). I'd like to tinker and make my own 1000 core (not a million!) circuit board, it sounds like a lot of fun.

[@MasticinaAkicta]

That are allot of chips. But good to see that ARM is so useful. Most consuments only get to meet them in their printer or their tablet.

[@scar_robots]

Do you know what the floating point performance of the machine will be?

[@BoogiemanXXL]

Really dumb question: A lot of simulation work is done on high end GPUs as far as I know, because GPUs essentially have sometimes thousands of cores which can be used for parallel workloads. I assume it's because a CPU is more versetile in it's instruction set or because GPU cores are much lower clocked ore something like that. But I also assume that there is some other much more glaring issue?

[@jakobforpresident2459]

I want to know more about this!!!

[@KarlFFF]

Amazing stuff, but why link them in a toroidal surface? also I am not quite sure I understand what that means... Is it to minimize the distance between any two cores?

[@Betacak3]

Wow. What a cable management.

[@LunaProtege]

So... Its been... One year? Two years? Since this video went up. I'm curious as to what progress has happened in the year since then.

[@Scotty-vs4lf]

i have a question. are these running like a 1 million core cpu, or is it wired differently?

[@GarrettGrimm]

I wanted to click that "How Computer Memory Works" box but there's no annotation fyi. Just ending up searching. Cool vid!

[@seanski44]

Thanks, will sort

[@ruthlessadmin]

Why not use GPUs? It seems like the way to go for massively parallel floating point processing these days. From what I understand about ANNs, you don't really need to do any integer maths, and the problem isn't the speed of an individual core, but how many you have, which is exactly what a GPU is good at...

[@Delfigamer1]

ARM cores tend to be simple yet flexible, which is probably one of the reasons why they use them. Since they are simple, we can easily spam them; but, unlike GPU cores, they won't choke over anything harder than linear algebra.

[@paulanderson79]

Cooling issues perhaps?

[@deadsi]

Partly to do with funding too maybe? There's a whole lot of these human brain modelling projects, this one seems to be one of the smaller ones

[@TheFearsomeSnyder]

because simulating a NN as a higher dimensional matrix, which would be the way to go, is even more computationally expensive then using custom designed ARM processors that where designed to mimic a neural network. A general rule in CS: the more specific the (design) task of your processor, the less energy/transistors it use to perform the same computational work. A human brain works in a very specific way, which accounts for our skill the observe patterns in out environement, or our amazing ability to self-learn, however, we're unable to perform many 100*100 matrix multiplications per second.

[@jackhales6179]

GPUs are meant for doing one thing - opting to the screen, however that's useful, have the cores do all the computation and have most likely a small rack of high-end graphics cards opting to the screen, etc... That's how I guess it'd work. :-)

[@mrprototype438]

Spends a billion dollars on a super computer and 50 bucks on cable management. :/

[@yanwo2359]

+Mr Prototype They had "a PhD student" wire it. Should have had me do it. But from photos I've seen, like equipment at CERN and big telescopes, wiring messes are common. How does anyone find and correct the bad cables and connectors?

[@FirefoxisredExplorerisblueGoog]

+Yan Wo You could use something like a blueprint. On a side note... have you ever considered the "cable management" inside your own brain? I hope you don't have OCD, if so: I'm sorry ;).

[@swunt10]

+Yan Wo by looking at it or following it by hand. which is something you can't do if some idiot managed to cram all the cables (most of them longer then actually needed) into some sort of cable box or tied up with cable binders. that makes changing out wires nearly impossible, inefficient and time consuming, especially since in science or development you need to fiddle around with it all the time.

[@mrprototype438]

I saw that rats nest and instantly thought of my switch rack at work.

[@TDRR_Gamez]

Chuper computer

[@mantasreika]

this is amazing I hope this technology advances for society's advantage

[@MsSovereign1214]

just wondering how much ram and flops does the thing pack?

[@caballopalido]

AH MANCHESTER. THE WORLDWIDE CENTER OF ARTIFICIAL BRAIN BUILDING

[@stevefrench4940]

So they would need an entire mini warehouse to model a human brain? Amazing.

[@Chr0nalis]

Why ARM? Why not clusters of fpga's?. I can see some Spartan 6s but I assume they are just do interconnect logic/routing. I am glad to see that something like this is finally built but the way I imagined is instead of using processors we could use fpga clusters with an sram under each fpga (on the backside of the pcb). You could model orders of magnitude more neurons that way.

[@PietroAzzari]

1% of the full human brain capacity! It's huge! As somebody would say "we are only 7 doublings away from the whole thing". It seems like genome sequencing 7 years before first successful sequencing

[@ruben307]

Pietro Azzari a doubling should be every 2 years after moore so in 14 years we have the brain capabilities. And after that they will surpas us fast.

[@Infinite_Omniverse]

Question: What would be, regarding the laws of physics/the universe, the most powerful computer ever (in terms of how fast it can compute)? Does the Bekenstein bound and the Bremermann's limit describe said computational limit?

[@unaliveeveryonenow]

+Yanna What, do the limits you mentioned seem too high or too low to you? Both of them are science fiction compared to the current state of technology. Both of the limits rely on the notion of a self contained-system and are useless at least until you find a self-contained system.

[@DarthBunny314]

+Yanna Pretty much yes. The Bekenstein bound basically limits information storage to the entropy of a black hole (for a given volume / surface area). Essentially, if a way could be found to practically extract information from it, a black hole would be the theoretical limit for both storage capacity and computational speed.

[@asdf30111]

+Yanna Do remember we are still learning about physics/the universe. We can only know so much with so much accuracy. Their is no true way to find a limit to the most powerful computer. We do not know what we do not know.

[@mustanger1966]

+Yanna I recall a Vsauce video where, towards the end, he shows a calculation for the maximum number of bits that could be calculated given that all the mass in the universe is converted into the most efficient possible computer and is allowed to compute for the duration of the universe before it runs out of usable energy. He came up with ~1.1664x10^230 bits of information. /watch?v=C6eOcd06kdk

[@asdf30111]

mustanger1966 But seeing that for a long time we did not about dark matter and dark energy, their is no way to know how much it can calculate. For all we know dark matter is blob like and can forever break into two with out losing any properties allowing for as many bits as you need. Also even with finite energy a perfect fractal computer can do infinity processing for infinite time. We can not possible know limits to technology. The computer Vsause was talking about was most efficient possible imaginable computer. Not the most efficient possible computer. Big difference.

[@RealCheesyBread]

These guys are going to map the human brain, and hopefully bring us Nerve Gear!

[@brentdaignault7565]

How about an update. Is the project finished, how is it going? Did they get to a million cores? Brady?

[@bastardtubeuser]

I'm just being cheeky but we should be parading Steve Furber around like Woz, telling his story over and over worshiped and transported from glorification to glorification. i suppose he Steve still works, good on him ! a real british hero for the ages. every day of his work is gift from god.

[@MigranBTW]

Those damn Spinnakers with they green backs and grey processors!

[@dunnobutwayne]

4:55 aaaah that cable management....

[@Liberty4Ever]

Interesting project, but how will this model quantum effects in the brain? This still looks like a big fancy calculator, no matter how complex the program. You can't model quantum effects using pseudo-random number generators or any other deterministic processes.

[@aron8999]

0:07 Damn spinnakers!

[@boberek007]

Coop772 In most countries where the metric system has been in use for generations, people use it exclusively. UK however only adopted it recently and reluctantly so it's normal for them to use either imperial or metric units depending on the situation. I'm guessing he just got so used to both that he converts between units freely without even thinking about it. There probably exist 2 sets of specifications for the equipment, one for Americans and one for the rest of the world lol

[@bonnome2]

They do have some knowledge about human memory, long term memory takes at least 2 years to fully form. The long term memory is located over the entire neocortex. This is basically the entire outside of the large human brain.

[@michaelhawthorne8696]

Coop772 I can't reply to your comment for some reason. So I'm doing it this way. The person in the video is clearly English and of an age where he would have grown up with the Imperial system. As he got older and the Metric system took over, there would be the tendency to swap between the two systems depending on the thought process at the time. As a Brit myself and of the age of 52 (in November lol) I too do the same thing, Although the majority of my schooling was in the Metric system (From 1972 onwards) I can visualise dimensions easier in the Imperial but often use the Metric system for many other things. We haven't been using the metric system long enough for this kind of thing to disappear.

[@xDMrGarrison]

This is so damn cool...

[@Roxor128]

Is there any particular reason for picking ARM CPU cores over GPUs?

[@clangerbasher]

How many watts does it use? And how much does 100k box cost?

[@achrafelamrani4937]

any idea what language they are using for the software ?

[@teknifix]

But you haven't answered the real question! Does it play Crysis?!? :)

[@Faxter313]

+teknifix well no, it can't. An artificial neural network is designed for different purposes. As far as my knowledge reaches - at this time it is not possible to make a ANN run any game. It is a massive parallel structure and is inefficient at sequential problems.

[@teknifix]

Faxter313 I know. I was just referencing an old joke people used to make when talking about their gaming rigs being able to play the first Crysis game when it came out.

[@emperorSbraz]

+teknifix i was looking for this comment. :D

[@richfiles]

+teknifix It won't run Crysis, but it probably could be taught to _play_ Crysis

[@TheRisingBuffalo]

+teknifix 20fps

[@user-rq5sn7zc5l]

The guy says we want ~1000 neurons per core, then says we have ~256 neurons per core, proceeds to say 'we're close!', less than 30% of the project's expectation.... Where's the beer....

[@SuperdoggyMusic]

All your cores are belong to us. :P great video.

[@grywacz]

I wonder. As long as this brain is not required to work with human real-time stimuli, what's the problem with it being 1% of a human brain in terms of volume? Wouldn't it be possible to go to ~100% by running it multiple times with different state? A rather common trade-off between computation space and time?

[@FishKungfu]

Very cool research! Maybe the ip address of the robot mouse should be pixelated out?

[@RobertMilesAI]

Fish Kungfu It starts 192.168, so it's a local network address, you'd have to already be connected to their network to access the robot, so it's probably not a problem.

[@FishKungfu]

Robert Miles I realize that, but that's assuming you trust everyone on the network, and you trust that no unauthorized person can get on the network. A little more paranoia never hurts. :-)

[@HiAdrian]

I'm sure that's a local IP :)

[@AtheistExpert]

+Fish Kungfu dropping infected thumbdrives in their parking lot AS WE SPEAK.

[@FishKungfu]

KatyPeezy Perfect. I'll install the Raspberry Pi behind the climate control panel in the janitor closet. ;-p

[@jmm1233]

that little robot got a big brain

[@feilox]

looks like they using sata 3 connectors? is that correct?

[@UnitZER0]

what if we took a donor brain, and then scanned it using x-ray tomography, or some other very accurate method, and scanned it perfectly into a computer. Then we used that scan to construct a perfect replica of the donor brain. Then we booted it up. What would happen?

[@awaken69]

how does this architecture compare to IBM's TrueNorth?

[@CariagaXIII]

but will it blend?

[@saltyman7888]

no blender

[@davecrupel2817]

CariagaXIII oldest joke on youtube. lol

[@Satchboy71]

18 cores x 48 chips x 24 boards x 5 frames x 10 racks = Merry Christmas!

[@NitWomba]

Wait wait wait! They're actually using ARM cores that are commercially available and making networked boards themselves. If the Manufacturers themselves start to make networked boards I can easily foresee a 100-fold reduction in size and maybe 10-fold reduction in power consumption on their first iteration!

[@JaredReabow]

Why not GPU'S rather than cpu's? they would give much higher density

[@Nuriyasov]

Jared Reabow Maybe because GPUs are not really well suited for uploading data to system memory? The GPUs are intented for displaying the calculation results on the computer screen, not sending the data back to the client. Downloading data from the GPU would probably be the greatest bottleneck in such a setup

[@woroGaming]

It sounds like the entire board operates like a combination of CPU/GPU qualities. The main power of a GPU is that it is capable of processing information by using multiple cores paralel, while a CPU prosseses information on one core at the same time. The strength of a CPU lies in the versatility of each core, while the power of a GPU lies in the cooperation of multiple cores combined. (at least, according to my knowledge of the subject matter, which is not a lot) So by building a board filled with the versatility of CPUs and using these like a GPU (making the CPUs cooperate with eachother) you get one powerful machine.

[@SSBMPWNER2]

+Timur Nuriyasov Except, IIRC, this type of implementation is exactly what the Nvidia Telsa cards were designed for. On top of that, with proper opencl programs, you'd only have to interact with system memory when you wanted to actually read out the status or when a gpu needed more data. In both cases, a well written program could easily make sure these system memory interactions never slowed the calculations.

[@Nuriyasov]

Kiba Urufu I guess they could have gone for Nvidia Tesla, but I imagine it would not be economically viable. See, these kind of enthusiast cards are exponentially more expensive than the mainstream GPUs we usually see in mining. Another thing is that it seems that communication is far more important in this system than calculation. What is the point of connecting so many computers if a slow GPU download will ruin it all? Also, I don't think it would be possible to avoid client memory interactions, last I checked GPUs didn't have their own network stack

[@souslicer]

+Timur Nuriyasov false. gpu's accelerate the gradient descent or whichever learning process, and can parallelize a feed-forward neural network. it's not just for video

[@notyou5267]

Does anyone know what CPUs are these (exact model), googling 18-cores ARM CPUs didn't help :(

[@stanrogers5613]

The chips are custom for the machine/project, but they use ARM968 cores.

[@scottwatschke4192]

Impressive.