IBM 'TrueNorth' Neuro-Synaptic Chip Promises Huge Changes -- Eventually

JakartaDean writes: Each of IBM's "TrueNorth" chips contains 5.4 billion transistors and runs on 70 milliwatts. The chips are designed to behave like neurons—the basic building blocks of biological brains. Dharmenda Modha, the head of IBM's cognitive computing group, says a system of 24 connected chips simulates 48 million neurons, roughly the same number rodents have.

Whereas conventional chips are wired to execute particular "instructions," the TrueNorth juggles "spikes," much simpler pieces of information analogous to the pulses of electricity in the brain. Spikes, for instance, can show the changes in someone's voice as they speak—or changes in color from pixel to pixel in a photo. "You can think of it as a one-bit message sent from one neuron to another." says one of the chip's chief designers. The chips are designed well not for training neural networks, but for executing them. This has significant implications for consumer AI: big companies with lots of resources could focus on the training, which individual TrueNorth chips in people's gadgets could handle the execution.

Comments

What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

5.4 billion. Bound to be a few bad actors in there. All hell breaks loose? IBM stock tanks?

Re:What Happens When One Transistor Goes Rogue?

[Shompol]

Neural networks are simulations of how brain works. You can lose a significant part of your brain yet change in cognitive abilities will be barely noticeable. Same principle applies to neural nets, including this one.

Re:What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

Their brains are intact. Physically, at least.

Re:What Happens When One Transistor Goes Rogue?

[NotQuiteReal]

You can lose a significant part of your brain yet change in cognitive abilities will be barely noticeable.

I'll drink to that!

Re:What Happens When One Transistor Goes Rogue?

[Dr_Barnowl]

They were trained to be Republicans by their environment.

As such, they clearly deserve our pity. And possibly some nice soothing drugs.

Re:What Happens When One Transistor Goes Rogue?

[SQL Error]

You mistake your wife for a hat.

Re:What Happens When One Transistor Goes Rogue?

[PopeRatzo]

You mistake your wife for a hat.

That was how we ended up getting married. I thought she was a hat and promised to just put my head in.

Re:What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

Please cite any papers or sources for this.

My understanding is that the younger we are, the more we can lose of our brains without losing too much cognitive abilities.
There are cases of very young children losing an entire half brain, yet function well (~90%).

However, losing the same for an adult would be catastrophic as the brain has become less plastic both physically and mentally.

A neural net is not much more than a complex weighted average. Complex usage depends on how you manage sets of these in relation to other types of function to create desired results, which often is just a fuzzy pattern matching. However, neural nets internals are very much considered "black box" so any assumptions about it would need to be backed by type and variation of training, but is not a given.

A neural net and a brain are two completely different things. You can perhaps simulate input/output of neurons, but we have no idea how to simulate/emulate brain neuron internals or even how higher cognitive functions emerge from seemingly chaotic activity, or if that's just a good guess and not even remotely true in reality.

Beware of weakly founded assumptions.

Re: What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

Good book!

Re:What Happens When One Transistor Goes Rogue?

[reboot246]

At least they have a brain. Democrats are safe from brain-eating zombies.

Re:What Happens When One Transistor Goes Rogue?

[Archtech]

It never ceases to amuse and baffle me how even intelligent, educated Americans (such as slashdotters) allow themselves to be lured into vicious "Republican-Democrat" battles. Isn't it obvious that Demoblicans and Republicrats are just the two hands of the same power? Every minute and every quantum of attention and passion you devote to slanging off the "other" party is a minute and a quantum of attention wasted; because the American political circus has been carefully set up so that neither party can ever win decisively. Instead, you attentively watch a series of more or less random fluctuations in fortune, and whip yourself up into a rage about the character defects of the other party's politicians, all the while ignoring the psychopaths in your own chosen party. And you will never succeed in changing the government's policies by any exercise of your votes - just look at what Obama promised before BOTH of his elections, and how he gave you Dubya's third and fourth terms when you kindly elected him.

When will we see a serious discussion on Slashdot about the underlying political system that controls both parties, and excludes everyone else? Why doesn't anyone seem to care about the impossibility of voting for a political leader who doesn't want to conduct genocidal foreign wars? How about a government that reins in the banks and declines to follow the orders of billionaires? Why don't any of you seem even slightly interested in government of the people, by the people, for the people? (In case you hadn't noticed, what you currently have is government of the people, by the servants of the rich, for the rich).

Re:What Happens When One Transistor Goes Rogue?

[morgauxo]

Because most people are stupid and humanity is a hopeless case. I wonder what the neadertals and denisovans were really like. Maybe the wrong homo won.

Re:What Happens When One Transistor Goes Rogue?

[Applehu Akbar]

"At least they have a brain. Democrats are safe from brain-eating zombies."

But only if the food they eat is labeled for any ingredient or process they might be irrationally scared of.

Re:What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

And your wife heard what she wanted to hear. Can you blame her? I think not!

Re:What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

Guess you missed that whole Bernie Sanders for president thing. It's not like we don't know. It's that we know we can't change it over a Slashdot post

Re:What Happens When One Transistor Goes Rogue?

[Anonymous Coward]

It never ceases to amuse and baffle me how even intelligent, educated Americans (such as slashdotters) allow themselves to be lured into vicious "Republican-Democrat" battles. Isn't it obvious that Demoblicans and Republicrats are just the two hands of the same power?.

The only differences between a Demoblican and a Republicrat are: What religion they follow and what time is best to kill you.

It's either GAWD or GLOBAL WARMING as a religion
It's either "kill it in wars, let it be born" or "kill it in the womb, but never send it to war"

Positronic technology?

[Anonymous Coward]

I'm wondering if you connect some of these together, if you could create a positronic brain.

Re:Positronic technology?

[Shompol]

Electronic brain. You would need to invent positronic computers first, or steal the tech from Silicoids.

Re:Positronic technology?

[gl4ss]

it's already connected some of these together.

but the network can't train itself. kinda strange anyways. for a neural net that can't train itself it looks kinda big. how much can they do with a single true north chip?

Re:Positronic technology?

[ceoyoyo]

Problem is, if your positronic brain leaks you get an antimatter explosion.

And so the rise of the machines, yippie.

[Anonymous Coward]

So which shall it be? Cylons or Skynet?

Re:And so the rise of the machines, yippie.

[aristotle-dude]

So which shall it be? Cylons or Skynet?

Original Cylons or Reboot? In the end both Skynet and the Reboot Cylons ended up nuking humanity. So it is 6 of one or half a dozen of another.

Re:And so the rise of the machines, yippie.

[Anonymous Coward]

So which shall it be? Cylons or Skynet?

Republicans.

Rat Overlords

[pubwvj]

You will be ruled by the King of Rats...

I think not.

Irony is not lost on silicon.

Re: Rat Overlords

[Anonymous Coward]

I for one welcome our rat overlords

Sorry. Couldn't resist

Re: Rat Overlords

[pubwvj]

I couldn't resist setting you up with the straight line. You're welcome and thank you for responding! :)

Correction to summary

[ClickOnThis]

TFA (and its accompanying picture) indicate that 48 (not 24) chips are wired together to simulate a rodent brain.

Re:Correction to summary

[Anonymous Coward]

...48 (not 24) chips are wired together to simulate a rodent brain.

Are they actually simulating a rodent brain or do they just have the same amount of "neurons" as a rodent brain?

The former is very exciting if so but from what I've read it seems to be the latter.

Re:Correction to summary

[ClickOnThis]

Thanks for the improvement.

Re: Correction to summary

[mbeckman]

IBM is not simulating a rodent brain. They're not even simulating neurons, since nobody knows how neurons work. And IBM isn't claiming to, despite the lie in Wired's headline. Some AI scientist simply hope that they don't have to know how neurons or brains work, because if they just put enough not-neurons in a not-brain network, that magically, intelligence will emerge. It's like putting a barrel of nuts and bolts in a spinning cement mixer and hoping a car emerges, or maybe a bicycle. But billions of times less likely.

Re: Correction to summary

[Anonymous Coward]

since nobody knows how neurons work

Knowing how something works is not a binary statement, where either we know nothing or everything. We know a lot about how neurons work, and they can be simulated on many levels. A common question for a lot of processes is what level of functionality is required to get a process to work. There are processes that work quite well with just a high level view of signalling between neurons, which is easy to simulate or make electronic versions of, while other processes depend more chemical interactions and are more subtle than just signals, especially if trying to understand how some biological processes can fail, which can be quite different from how they work normally.

Re: Correction to summary

[Anonymous Coward]

IBM is not simulating a rodent brain.

Except this was in part developed as part of the DARPA SyNAPSE program, which includes a later phased of modeling a mouse brain on a chip, and ultimately something on par with a cat brain that can be used in a robot that interacts with its environment. Of course there will be other uses for such hardware too, and it is expected they will be commercialized before the longer term goals are reached.

They're not even simulating neurons, since nobody knows how neurons work

But researchers already have a good idea of how the neuron works. There is still a lot to learn about all of the biochemical interactions, but there is also plenty to be done with just the electrical signaling that happens on top of that.

Re: Correction to summary

[mbeckman]

Coward,

Any neuroscientist worth his salt will tell you that we do not know enough about neurons to accurately simulate them in software or hardware.

Re:Correction to summary

[robi5]

Evidence for the singularity! By the time I get to read all comments about new tech, the transistor count doubles!

Re: Correction to summary

[robi5]

> since nobody knows how neurons work

This would just rob the verb 'know' from its meaning for everything other than pockets of mathematics. For it is the case that even physics isn't fully figured out, what with reconciling general relativity and quantum mechanics, to name one gap, let alone chemistry, which sits atop of physics, not to mention biology, which sits atop of both.

There is a huge difference between a taxi driver not knowing how the neurons work, and a neuroscientist not knowing how the neurons work. The difference isn't only in some abstract sense; neuroscience actually generates a stream of useful results, e.g. in healthcare.

I'd also guess that when it comes to our lack of understanding about how the brain works, or how consciousness arises, it's more to do with how the neurons are arranged into a network (in terms of structure and plasticity) as opposed to being limited by the knowledge of individual neurons. It would surprise me tremendously if a perfect neuron model led to the understanding of the brain, but it wouldn't surprise me at all if, once the brain's working is better understood, it turned out that a lot of detail about how individual neurons work are inconsequential or somewhat accidental, with much of neuron level complexity simply resulting from the fact that the neuron is of a complex, very large 3D shape with general chemical, electrical and molecular processes, which makes it inherently intractable. Let's not forget that tasks as simple as the three-body movement or laminar flow are still just crudely approximated in software; a single protein folding itself is complex; yet we understand how muscles move etc.

We don't have to know _everything_ in order to know _an awful lot_.

Re:Correction to summary

[Anonymous Coward]

Currently you can reincarnate as a rodent. How happy does this make you? :)

Re: Correction to summary

[dargaud]

Not knowing enough is not the same as knowing nothing.

Re: Correction to summary

[Anonymous Coward]

Unfortunately you can't define what intelligence is, so these not-neurons in a not-brain network may well be producing it and you wouldn't know. I mean your strawman analysis of the entire field of neural computing is missing one important fact: it does work, and cars do emerge. Or, at least, best-of-class speech recognition, image recognition, etc. etc. etc. It's not about creating "intelligence", whatever the fuck that is, it's about solving hard problems which humans happen to find quite undemanding. And if you don't think there's any connection at all between the success of humans at those tasks, and the success of neural networks at those tasks, then you really are lacking any form of imagination, causing me to wonder how long it will be before computers surpass the intelligence of Slashdot commenters such as yourself.

Re: Correction to summary

[Anonymous Coward]

Again, you're trying to force things into a binary false dichotomy. In just about every field, it is impossible to fully simulate a situation either due to lack of knowledge or lack of processing power. Plasma physicists can't model every particle, and instead have to resort to approximations that vary from PIC up to MHD level simulations. Electronic simulations can't capture every parasitic element, and have simulations that vary in detail from PEEC to simulations just covering the schematics. The level of simulation needed and the resulting accuracy depends on the situation and what you actually want to look at.

As already said, the question isn't necessarily a simple as, "How do neurons work," but, "What aspects of their function are important in what cases." Electrical signals alone are enough to simulate normal preprocessing functions of nerves in the retina and parts of the visual cortex. This may be enough for a lot more complex operations, even if it doesn't allow full simulation of medical conditions, in the same way that a simple SPICE simulation can model how a circuit functions, but not what happens when a component fails or there is a massive RF source near by.

Re: Correction to summary

[drinkypoo]

It's like putting a barrel of nuts and bolts in a spinning cement mixer and hoping a car emerges, or maybe a bicycle. But billions of times less likely.

That's a stupid thing to say, because nobody actually knows what makes intelligence work; it might well be a combination of enough raw matter of intelligence, and enough sensory input to do something useful. But we know what makes fasteners work, and it's not putting them in a cement mixer and tumbling them.

Re:Correction to summary

[Anonymous Coward]

Are they actually simulating a rodent brain

Actually, they're simulating the brain of IBM's CEO Ginni Rometty. Same thing I guess, she kind of looks like a rodent too.

Re: Correction to summary

[mbeckman]

Nobody said we know nothing. I said we don't know nearly enough.

Re: Correction to summary

[mbeckman]

"I am having lunch on the Moon this week!"

"No, you're not."

See, dichotomies work all the time. Especially when you have facts to back them up.

All your handwaving about how much knowledge is enough for useful simulation is meaningless, because we aren't talking about useful simulation. We are talking about reproducing the intelligence of a rodent brain.

The other simulation examples you cite are all experiments based on knowledge we already have. You can't model something you don't understand, and we do not understand ANYTHING about the relationship between neurons and intelligence. We don't know how memories are stored, or where they're stored. We don't know how decisions are made, or even if they're made in the physical brain at all. We know so little tht we can't even estimate how much more we need to know.

Nobody is building a mouse brain this week. Or this year. Or even this decade and I doubt this century.

Re: Correction to summary

[mbeckman]

There is a huge difference between a taxi driver not knowing how the neurons work, and a neuroscientist not knowing how the neurons work.

My point is that there is not huge difference. In fact, I think the taxi driver is in a far better position, because he isn't lying to people telling them that he is close to reproducing rodent and cat intelligence from a simulation of not-neurons based on not-knowledge of intelligence and neural biology.

Re: Correction to summary

[robi5]

For the record, you originally said: 'They're not even simulating neurons, since nobody knows how neurons work.'

Re: Correction to summary

[robi5]

Someone with a medical problem would better rely on the person whose knowledge about neurons, synapses, neurotransmitter reuptake or beta amyloid plaques is infinite relative to that of a cabbie, unless of course he needs to get to the hospital first :-)

Re: Correction to summary

[ceoyoyo]

Or, you know, like building a robot arm out of metal and electrical motors and hoping it can lift things like a real arm made out of bones and protein.

Somewhere between the ridiculously optimistic AI researchers (who mostly got sense slapped into them in the sixties) and the cargo cult neuroscientists, there's a middle ground where lots of serious research is happening.

Re: Correction to summary

[Immerman]

>We are talking about reproducing the intelligence of a rodent brain.

No. We're not. We're talking about *simulating* a rodent's brain to the limits of our current understanding

I really doubt anyone expects it to be successful at simulating rodent behavior. That's not the point. Doing so would be pretty much useless anyway. The point is to see how it fails, and how it kind of succeeds, and thus gain insight into how much we don't know, and what directions future research should take. We have to start somewhere, and this is the first step into taking decades of neuroscience research and converting it into a basic simulation so that we can begin to refine our understanding. With such low-power simulating hardware it even opens the door to horrifying but potentially extremely informative studies such as replacing specific portions of a rodent's brain with a simulation. If we replace the motor-cortex with a simulated one, can the rodent still function, and what shortcomings does it demonstrate?

Re: Correction to summary

[Anonymous Coward]

Nobody is building a mouse brain this week. Or this year. Or even this decade and I doubt this century.

Because you say so. Because we need to understand the fundamental essence of a neuron in order to simulate large-scale intelligence.

That's why all of our simulations of galactic formation are so far off the mark when compared against empirical observations. After all, we don't even have a fundamental understanding of the nature of quarks, so how could we possible have any understanding of baryonic matter at large scales?

How can we possibly build cars if we don't even understand what quarks are made of?

Re: Correction to summary

[mbeckman]

We know things about neurons, but we do not know how they work. Just as I know things about the Navy Seals, but I don't know how they works. The difference is that knowledge about how the Navy Seals work is possessed by some humans. Knowledge of how neurons work is possessed by no human.

Re: Correction to summary

[mbeckman]

>We are talking about reproducing the intelligence of a rodent brain.

No. We're not. We're talking about *simulating* a rodent's brain to the limits of our current understanding

Sorry, no. The Wired article title in "IBM’s ‘Rodent Brain’ Chip Could Make Our Phones Hyper-Smart". The title is derived from IBM scientist Dharmendra Modha's description of what IBM built: "You’re looking at a small rodent,”

The claim, at least by Wired, is that IBM has simulated the intelligence of a "small rodent."

The point is that AI researchers and the media keep recklessly spewing outrageous, but unjustified, claims about what they've achieved.

They need to stop.

Re: Correction to summary

[mbeckman]

But we are not talking about people with medical problems. We are talking about claims of achieving the intellectual complexity of a rodent.

Re: Correction to summary

[mbeckman]

Unfortunately you can't define what intelligence is, so these not-neurons in a not-brain network may well be producing it and you wouldn't know.

The burden of proof is not on me, but on those making assertions about IBM's chips achieving rodent brain capabilities. I don't need to prove anything, and demanding that AI researchers and the media support their claims with facts is not a strawman argument.

Re: Correction to summary

[Anonymous Coward]

See, dichotomies work all the time. Especially when you have facts to back them up.

That wasn't a dichotomy, nor has anything said by anyone in this thread involved backing things up with facts. However, if you actually look into things, like the goals of the actual SyNAPSE program and see it involves actual simulation of mammalian brains, and includes works from neurologists (unless you want to double down on the "no true neurologist" approach you also tried earlier).

Re: Correction to summary

[mbeckman]

I agree, except that all that's been achieved so far -- self-driving cars, speech recognition, etc -- is just automation, not intelligence. None of these artificial processes are intelligent, they are simply reliable at solving a small class of problems to a certain level.

Re: Correction to summary

[robi5]

I'm not necessarily disagreeing with your overall point, just took issue with what you said earlier: 'nobody knows how neurons work' as it vacates the meaning of 'know'. Using your term, we didn't 'know' how gravity worked even after Newton's and Kepler's work, still we were able to construct accurate ballistics, because we still knew something. So your use of 'know' just represents some possibly unattainable level of knowledge in natural sciences, and with that definition, this word would be meaningless, since we could say 'we don't know how X works' no matter what X is.

Whereas with the more customary meaning of 'know', which I'm also using, we can safely say, that we know to some extent how the neuron works; researchers and medical professionals possess an awful lot of knowledge about how the neuron works. Of course, without picking some metric, we don't know how complete our understanding is when it comes to gravity or other physical phenomena, and similarly we don't know how complete our understanding of a neuron is, and we can safely say our understanding of gravity is very useful for the things we currently envision we can use the gravity model for, while we're not there at all when it comes to neurons.

But we can definitely say that our current knowledge (model) of neurons is useful for a lot of things, i.e. we can't meaningfully say 'we don't know how neurons work'. Maybe you wanted to say, 'we don't know enough about how neurons work to serve the purpose of the goals described in TFA'.

Re: Correction to summary

[mbeckman]

Using your term, we didn't 'know' how gravity worked even after Newton's and Kepler's work, still we were able to construct accurate ballistics, because we still knew something.

That example is not congruent with the AI claims made here.

First, we still do not know how gravity works. We have observed its effects and have drawn conclusions that were then formulated into physical "laws", but nobody understands the mechanisms of gravity.

Second, gravity is a very simple process compared with the processes of intelligent thought. We don't even know that thought occurs in the brain. The brain might just be an I/O interface to a completely different repository of intellect that we haven't discovered yet (e.g., what some people call the soul). Maybe, maybe not. We just don't know. Nobody has proven that intelligence resides in the brain. We've only poked at it and observed effects.

Given that level of uncertainty, nobody currently understands neurons and their role in intelligence to do anything more than wild, unprovable guesses.

Re: Correction to summary

[Immerman]

>The claim, at least by Wired...

And there's the answer to your complaint. Why would you assume the Wired article has more than a passing resemblance to reality? The first rule of science journalism is "assume the journalist has no clue what they're talking about". You read between the lines, viewing sensationalist speculation through the lens of science-based cynicism, and then research primary sources if you're still interested.

Re: Correction to summary

[Anonymous Coward]

According to this, nobody knows anything except maybe certain mathematical truths. Which is why I originally said this use of the verb is not a meaningful one.

Re: Correction to summary

[Anonymous Coward]

I do not think it is matter knowing how a neuron work. I am pretty sure chemical inputs are received through dendrites which cause a neuron to build an electrical charge. When enough of a charge is built up the neuron fires an electrical charge which causes chemical changes in neurons connected to the firing neuron. This does not explain how system of neuron function, how connection are strengthened or weakened and a whole host of other questions.

It is pretty easy to learn any note or cord on a piano. Knowing how to play any note or chord does not mean you can easily to play a master work by Beethoven.

Re: Correction to summary

[Anonymous Coward]

Nobody knows exactly how neurons work. However, in building neural networks (and I've done so myself) it has been noticed that artificial neural networks are quite insensitive to the exact type of artificial neuron used. This can make it quite hard for beginners to debug defective networks, and it also explains why DNA mutations generally don't lead to massive brain failures. Neural networks are evolutionary robust. And for that reason, the exact details of biological neurons are irrelevant.

Re: Correction to summary

[Anonymous Coward]

By that logic, nobody knows how computers work.

"Behave like neurons"

[Anonymous Coward]

Watch the clock, quit work right at 4 pm, and go get wasted?

Re:"Behave like neurons"

[JustAnotherOldGuy]

That was my take on it, lol.

Answer a question for me?

[Okian Warrior]

Neural networks are simulations of how brain works.

Apropos of nothing, since you're familiar with both neural nets and how the brain works, can you answer a quick question for me?

Neural nets have a left-to-right topology, where the inputs go in one side and the outputs leave the other side.

The brain doesn't do that - there's no "loop" in the brain where input neurons are processed on one side and output neurons exit the other.

This has always confused me about neural nets. If they simulate how the brain works, then how exactly *does* the brain work with inputs and outputs both on the same side?

Re: Answer a question for me?

[Anonymous Coward]

Each neuron is connected to many others. As such, the outputs feed into others and there are feedback loops as well as dedicated outputs.

Re:Answer a question for me?

[Anonymous Coward]

there's no "loop" in the brain where input neurons are processed on one side and output neurons exit the other.

Uhh, there are dedicated input and output parts of the nervous system...

If they simulate how the brain works

Neural nets in general are not simulations of how the brain works, but a set of algorithms originally inspired by the design of the brain. Some of them have been simplified or otherwise diverge, as they are developed for applications to other problems.

Re:Answer a question for me?

[Mr.CRC]

You're asking "what is the system architecture of the brain?"

This would be a good thing to have mapped out. In fact, I'm surprised this isn't done already. Or is it?

Instead of working with amorphous blobs of neurons, the real advances in AI will come when specialized subsystems can be taught, then initialized at will with the "teaching." Those systems put together into a larger system similar to an actual brain will be what leads to general AI.

Re:Answer a question for me?

[Shompol]

Apropos of nothing, since you're familiar with both neural nets and how the brain works

It's funny but the only reason I understand how brain works is because I know how computer neural nets work. There are many common aspects in both operation and shortcomings.

As far as your question goes, brain definitely has a distinct set of inputs (retinas, sensory, etc), but the output is known as "self awareness" and was not covered in my comp sci classes. It is likely that this development brings us one step closer to a working Skynet.

Re:Answer a question for me?

[SuricouRaven]

The output of the brain actuates lots of muscles, and a few glands. The 'self awareness' is a part of the processing.

Re:Answer a question for me?

[narcc]

The 'self awareness' is a part of the processing.

Why do you believe silly things without evidence? The answer to the self awareness question is a clear and unambiguous "we don't know".

Re:Answer a question for me?

[Anonymous Coward]

The entire brain is a control system for the body. Its inputs come from the sensors and its outputs go to the actuators, same as every other control system. INPUTS -> BRAIN -> OUTPUTS. That middle part is still somewhat mysterious :)

Neural nets don't tend to simulate an entire brain, though, so you can easily imagine that a patch of the brain takes inputs and outputs from/to other regions of the brain.

Re:Answer a question for me?

[Anonymous Coward]

The answer to everything is "we don't know". But Occam's Razor forces us to take OP's model as the best current model. Unless you have evidence that self awareness is some magic special thing, we should assume it's simply an artefact of the processing and survival strategies used by the brain. It is certainly inside the brain, unless you believe in other random Occam's Razor-abusing stuff like souls, so it's not an output of the brain, which was OP's main point.

Re:Answer a question for me?

[ceoyoyo]

Not all artificial neural networks are strictly feed forward. There are other designs that incorporate feedback but they tend to be harder to train and use (you have to wait for them to settle), so you don't hear about them a lot in connection with practical applications. One of the major types that is not strictly feedforward but is used a lot is the recurrent ANN, which is used in speech and text recognition, and natural language processing. In that type of network, the output produced by the previous run is fed back in as an input for the next run (the next word, for example).

The brain uses lots of different neural architectures. There are areas that use massive feedback, but other areas that are strictly feedforward. The type of ANN you're describing evolved from something called a perceptron which, as the name suggests, was inspired by models of the visual system. The mammalian visual system does a lot of feedforward processing.

Re:Answer a question for me?

[morgauxo]

The brain is hugely complicated with many inputs and many outputs and many many loops within.

A neural net is a very simplified version of a brain with one set of inputs and one set of outputs, and a very limited number of loops within.

Re:Answer a question for me?

[SuricouRaven]

You cannot observe the self-awareness thing directly (yet, anyway) but you can deduce the process occurs by observing inputs and outputs.

Re:Answer a question for me?

[narcc]

I certainly can. That's precisely what makes me self-aware.

You mean in others. As for the alleged deduction, it's depressingly weak.

Re:Answer a question for me?

[micahraleigh]

I studied brain theory and AI at USC in post grad.

This is a really great question.

Neural networks do not exist in nature anywhere for any species in the sense of the left-to-right pipeline framework you describe.

As with any simulation, there isn't going to be 100% parity with the real thing. It simulates neural networks in the sense that they are adaptive and produce pavlovian results, associative chains, etc.

Can't comment on to what extent the layout you describe (i.e. a traditional neural network) relates to what IBM has set up here.

Training

[Anonymous Coward]

... could focus on the training ...

It's difficult to train AI for real world events. There's the apocryphal story that photo recognition software trained with military tanks, instead learned to recognize clouds.

It seems that organic brains do have some built-in primitives: Visually, we recognize lines and shadows without training. See here.

Research demonstrates we are very effective at detecting eyeballs and breasts: I wonder how much of this is learnt.

Terminator

[Anonymous Coward]

"The chips are designed well not for training neural networks, but for executing them."

Bring your neural net over here...we are going to execute it.

"Eventually"?

[tlambert]

"IBM 'TrueNorth' Neuro-Synaptic Chip Promises Huge Changes -- Eventually"

So basically... the chips are thinking about it?

Low power = stacking?

[DigiShaman]

So if 48 of these dies can be stacked in a 3D package, it's only throwing off 3.36 watts of heat??!

Deep Dreaming Patents

[Anonymous Coward]

Look, they noticed that neural networks have made a comeback, so they dusted off one of the old neural network on a chip designs, packed in a few more elements and hey-presto, NEW PATENT OPPORTUNITY to capture any of the profits that the current investigations in neural nets might produce.

So the stuff of 1999, becomes the patents of 2015!
http://people.ee.duke.edu/~mbrooke/papers/1999/00833427.pdf

What I can bet is IBM won't make anything of this, beyond a patent, because making stuff costs money, employs people and is not very profitable, whereas patenting stuff grabs other US companies profits, requires only a few lawyer and is almost pure profit.

The "use it or lose it" patent reform would take care of IBM's trolling, if they want to patent this chip they would have to be a manufacturer. Like a trademark thats been left to lapse, so patents unused would die.

Re:Deep Dreaming Patents

[phantomfive]

A lot of the recent advances in AI have been using old algorithms, but taking advantage of Moore's law to use them on bigger problems.

Wow. Go IBM.

[Seatche]

It appears that you're growing the computer to limits beyond what I expected. Well done.

Re:Wow. Go IBM.

[Anonymous Coward]

I'm sure they'll be delighted to hear it. Can they have a cookie?

Re:Wow. Go IBM.

[Lodlaiden]

No. Cookies are for the kids that actually accomplish stuff; not for those that promise "eventually".

Numenta

[Anonymous Coward]

IMHO, Numenta is way ahead of the deep learning camp. Truly can recommend going to their website and read up on their ideas and technology. Also there is a video in their website that shows how IBM is trying to implement Numenta tech in silicon.

Reinventing the math coprocessor

[Etherwalk]

Sounds like IBM is pushing to make these almost a specialized chip for each machine. That sounds like your client's so fat it warps space-time approach in moderately thin-client world... There needs to be a major advantage before a math coprocessor for AI becomes viable at the consumer level...

Re:Brain

[hackwrench]

Well, it all depends on what the meaning of "brain" is.

More Snakeoil, Boys!

[Anonymous Coward]

Dharmendra Modha???? His earlier claim they created a computer as power as a cat brain was debunked here: http://news.discovery.com/tech...

Not really brain neurons

[Anonymous Coward]

They mean chips that execute large sized sigmoidal regression functions, not simulate brains! Real neurons (a) are massively more complex than this; and (b) we still don't know how they work -- for all we know there's binary computation happening inside bits of microtubule or in interactions with glia ... But then sigmoidal regression functions never make as many headlines...

Pffft.. So much easier to do it this way...

[doccus]

Just wire up the brains of a bunch of mice. No development cost. Just a little bit of feed and a pooper scooper...