Slashdot Mirror
Building Brainlike Computers
newtronic clues us to an article in IEEE Spectrum by Jeff Hawkins (founder of Palm Computing), titled Why can't a computer be more like a brain? Hawkins brings us up to date with his latest endeavor, Numenta. He covers progress since his book On Intelligence and gives details on Hierarchical Temporal Memory (HTM), which is a platform for simulating neocortical activity. Programming HTMs is different — you essentially feed them sensory data. Numenta has created a framework and tools, free in a "research release," that allow anyone to build and program HTMs.
It spent most of the time watching TV all stoned. Too many receptors.
to believe that man could create a brain is absurd. Only god could create a brain. Computer programmers seem to have a delusion that they can make something in the image of gods creation. You can make games, wordprocessors, email programs, no problem, those are easy, but to believe you can make something capable of understanding the world in all its god given glory is heresy.
Because it would signal the end of civilization...if computers can look like women (porn), feel like women (Realdolls), and think like women (have a brain, at least in some cases), then all procreation would cease and humans would suffer the same fate as the dinosaurs.
It's all been done before, perceptrons, multi-layered perceptrons, recurrent connections, etc, etc, etc...dunno why anybody would pay attention
...but it's all in my head!
blah blah blah
...comps get lazy and start reading /. instead of working?
Especially since the mad scientist involved didn't bother putting in a female brain for companionship.
YOU HEAR THAT, GOD? I WANT AN ATTRACTIVE SET OF BITS SENT INTO MY LITTLE UNIVERSE RIGHT NOW.
Oh, and fix the Middle East. Thanks.
This quote from the article is telling: HTM is not a model of a full brain or even the entire neo-cortex. Our system doesn't have desires, motives, or intentions of any kind. Indeed, we do not even want to make machines that are humanlike. Rather, we want to exploit a mechanism that we believe to underlie much of human thought and perception. This operating principle can be applied to many problems of pattern recognition, pattern discovery, prediction and, ultimately, robotics. But striving to build machines that pass the Turing Test is not our mission. Well, my goal is to build machines that pass the Turing Test, so I have to think about more than cortex. But more generally, one might wonder how much of intelligence it is possible to capture with a system that "doesn't have desires, motives, or intentions of any kind".
Perhaps because we invented computers to do what our brains aren't as good at -- namely, arithmetic and automating dull, repetitive tasks. If computers worked the way brains do, they'd get bored with doing their job and find something else to do.
I might be indecisive, but I'm not really sure. What do you think?
I see quite a few comments on how the development of such technology is a threat to the human civilization, but on the contrary it can mean that "humanness" or what makes us humans (the way we think etc) can be propagated in the form of machines through the universe even after the end of our planet.. I don't think I will be less human if my mind/thought process were moved to an artificial system (say a robot) from my natural one, may be this is the next step in evolution, evolving away from flesh and bones...
Awesome,
at least someone realizes that things can be computed on a platform other than Windows.
Plus, you don't have to worry that your brain will be busy sending out spams while it's training.
Since they (scientists) don't really have a full understanding about how the brain works then it seems to me that building a computer to work like one is a litle far fetched.
When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
Look, it's even put Slashdot as my home page! Isn't that nice. :P
127.0.0.1
Seriously! This is one of the funniest posts I've read all day!
Whooboy, "It's heresy!" That's a good one!
Because of the neocortex's uniform structure, neuro-scientists have long suspected that all its parts work on a common algorithm-that is, that the brain hears, sees, understands language, and even plays chess with a single, flexible tool. Much experimental evidence supports the idea that the neocortex is such a general-purpose learning machine. What it learns and what it can do are determined by the size of the neocortical sheet, what senses the sheet is connected to, and what experiences it is trained on. HTM is a theory of the neocortical algorithm.
While I believe that the HTM is indeed a giant leap in AI (although I disagree with Numenta's Bayesian approach), I cannot help thinking that Hawkins is only addressing a small subset of intelligence. The neocortex is essentially a recognition machine but there is a lot more to brain and behavior than recognition. What is Hawkins' take on things like behavior selection, short and long-term memory, motor sequencing, motor coordination, attention, motivation, etc...?
Immitation doesnt result in the best engineering, even though Nature has invented amazing things.
Please take your professional/scientific reviews to real scientific journals. Only bitter/ignorant jokes are acceptable on /.
We build brain-like computers. Are we then possible to make Insane computers? sociopath computers? or homocidal computers?
Do not look at laser with remaining good eye.
Medievals didn't understand the atom or crystalline structures, but they still made carbonized steel for armour. They had the wrong ideas about exactly how metal became properly carbonized and tempered, but they still came up with correctly tempered spring-like steels (IIRC similar to tempered 1050) without getting any of the "why" of it right.
I think someday we will be viewed as the medievals of AI. We occasionally make progress even though we really don't know what we're doing. Yet.
Weaselmancer
rediculous.
If we can grow a human ear on a mouse, why can't we grow a human ear on a human?
The fact is, women who act like actual people will have no problem getting ogled.
The snivelling harpies who bought into the, "We can do everything! We're women! We're better than men!" crap (you know the type - the ones who think they're princesses and that the world revolves solely around them) will be cast aside in favor of our animitronic boob-laden overlords.
Of course, this will see a good number of male genetics, ahem, dripping onto the ground instead of continuing as well. But in the end, we'll be left with sane women and men who can simply roll their eyes and somehow not manage to become infuriated over stupid arguments about whether the toilet seat should be left up or down.
I, for one, welcome the coming superhumans.
Hawkins and the people he's working with have come up with an approach that lets people explore possible uses of allowing a machine to learn in a way that's inspired by a process that may be part of how humans learn. They don't need a "full understanding" of how the human brain works to do that.
I know that you're merely trolling and don't actually believe what you say. Nevertheless ...
:-)
:-)
It's worth stating that unless you believe that the human brain contains magic (which 99% of your religious bretheren don't), then it is no more than a very complex arrangement of perfectly ordinary physical components, namely atoms and molecules. And if you don't think that we will in due course be able to arrange atoms and molecules as we wish, then you're very blinkered to the direction in which science and engineering are heading.
That said, the recreation of human brains is merely an interesting challange as far as practical engineers are concerned, and not a practical approach. The vast majority of us have no intention of actually taking that route because protein is such an inferior building material. Your alleged god (aka. blind evolution) only "chose" it because carbon is so damn versatile in conjunction with O and N and H, so a million different reactions occurred in the mess of the primordial soup. And one of them happened to work.
Well we don't rely on blind chance, but coerce the reactions in the direction we want, which gives us the chance to choose our materials more strategically. And we will.
There's not a chance in hell (trying to use your frame of reference here) of us producing "brains" that are *MERELY* as good as nature created in humans, because the equations that underpin ordinary physics and chemistry (and therefore molecular nanotechnology) say otherwise. Instead, you can expect "brains" a billion times our mental capacity and a trillion times our mental speed in due course. We know that it's possible (from theory, and by observing protein nanomachines doing it very poorly), but we lack the infrastructure to do it ourselves at present. It's many decades away, but hey, we're working on it.
You'd have to contradict the maths and physics of materials and biotech that says that MNT is possible before you can validly say that it's not. And with the intellectual depth of your contribution above, my guess is that you won't.
"The question of whether machines can think is no more interesting than [] whether submarines can swim" - Dijkstra
We expect computers to give the exact same solution or answer when their program is executed once, twice, ten times, or a million times. Humans however make mistakes, our biological brains are better at pattern recognition and face recognition... But our logic is fuzzy... sometimes we will give a wrong answer or make a mistake on a simple calculation. So perhaps the ultimate goal is not to build a computer that thinks like a human, but rather apply (perfect) computer technology where it is appropriate and apply (imperfect) human thinking where it is needed. Actually the notion of the Mechanical Turk (article on slashdot a few weeks ago)... this is the future of Artificial Intelligence...
Why do you think that people are going bonkers over the offshore outsourcing trend? It's like Artificial Intelligence... You ask a question over the phone, or via chat window, and your question is magically answered by the thinking thing inside the box. It doesn't matter what the thing is on the other end of the line... all that matters is that it gives you a reasonably good answer that helps you make progress in your business or personal life.
We already have seen the face of Artificial Intelligence... it is staring back at us in the mirror.
I can throw as many stones as I wish; my house is made of transparent aluminum.
I played with the picture recognition software and if you just make a dot and click add noise like 20 times it thinks it's a dog. I did that 4 or 5 times in a row with the same result.
If you fed a zombie a brainlike computer, would he be satisfied? or would you instead have to invent a robot zombie to consume said computer?
It's certainly possible. We make child soldiers and all sorts of things. I sure if we're brutal enough, we can make anything pretty psychotic.
The key thing is that is a complete working system we're not "making" it anything in the sense we make a desktop computer do something. If we were, it wouldn't really be brain-like. Instead, we're causing something brain-like to have proto-experiences. When the hardware (and low-level software) gets to be far more brain-like, to the point where from a logical topology standpoint it's difficult to tell the two apart, one can expect that these computers will be people like the rest of us, and subject to many of the same weaknesses. We'll know we've succeeded when we make a computer that's bad at math.
I am the one true god. However, as an atheist, I don't believe in myself. I guess I have a self-esteem problem.
The above comment has been modded Redundant. As of right now, there are no other comments on this discussion about Beowulf Clusters. Not one.
Why do you mention computers?
Exactly.
Socialist and corrupt are synonyms, so he was being redundant. How silly!
You mean hallucinating, pot slows the resistors, LSD turns all the lights to green and increases the speed limits.
Under the influence of Post-Cyberpunk Gonzo Journalism
Well, my goal is to build machines that pass the Turing Test, so I have to think about more than cortex. But more generally, one might wonder how much of intelligence it is possible to capture with a system that "doesn't have desires, motives, or intentions of any kind".
Not to mention, motor coordination, attention, short and long-term memory, cerebellar processes, etc... It's a little more complicated than Hawkins would have us believe, especially if you don't already know the answers. Fortunately, the secret of AI has already been found and written down for us many centuries ago. Check it out: Artificial intelligence from the Bible!. ahahaha... AHAHAHA...
Good timing for this one :/
- "Nobody came out that night, not one was ever seen. But Old Man Stauf is waiting there, crazy sick and mean!"
Neuroscientific theory indicates that we will not be able to build truly brainlike computers until we have gone beyond serial, John-Neumann-bottleneck computers into the realm of massively parallel (maspar) hardware and software.
Mind.Forth, a primitive but True AI, simulates the maspar human cortex by taking a few shortcuts based on the differences between neuronal wetware and computer hardware. For instance, Mind.Forth, unlike chatbots, has concepts. Whereas a brain will activate thousands of concept-neurons in parallel, Mind.Forth activates only the most recent instance of a concept, because computer hardware is more reliable in the short term than a single human nerve-fiber, which may be fatigued or even dead.
AIMind-I.com is another pretending-to-be-maspar artificial intelligence based on the original Mind.Forth design.
Mind for MSIE (for Microsoft Internet Explorer) is the JavaScript tutorial program (but still an albeit primitive True AI) that shows you how spreading activation flits from concept to concept in the serial computer pretendimg to be a maspar brain.
I'm just saying that the human brain is a thing made by god, and we can't copy it.
We certainly don't want god coming after us for IP infringment...the MAFIA is bad enough and they only have lawyers!
On a more serious note though why not? Pretty much everything we have done as a species to date is copying some process which occurs naturally in the universe. Since we learn by copying why not learn from the best?
I take drugs for bipolar tendency and have had 5 nervous breakdowns, so I have some ideas about how the brain goes wrong, I am afraid that the search for a perfect machine learning device may be a side track compared to explaining the mistakes the brain makes.
I have an engineering degree and a masters specialising in machine learning - but that was 13 years ago, I would be delighted in more pointers of the state of the art
http://www.cnbc.cmu.edu/Resources/disordermodels/ , on bipolar and neural networks, seemed promising at one stage but I had not the time, energy or rights to read the latest papers. [The web page is dated 1996]
Be Free: Free Software Tuition
Very interesting reading. /. in a long time.
This is the first piece of "stuff that matters" that I have read here on
Hasn't anybody read Dreyfus? It seems to me his critique of AI is the nail in the coffin for humanlike behavior. The basis for his arguments are that much of the human brain's calculations are non-representational, while everything a computer does is representational. Since computers must bind representations to things in order to manipulate them, they must contextualize the situation in order to determine how to apply representations... but in order to contextualize the situation you need to bind representations... and so we have an infinite regress. The human brain doesn't do this, instead, it responds to stimulus by strengthening nerve connections, in finely tuned discriminations unique to the individual shaped by circumstance. Instead of binding representations to a situation, the situation invokes the neural pathway. One cannot simply program this neural pathway in, snce it is finely tuned to the individual based on past circumstance, their omotion, personality, and physical body amoung other things.
There is a group of people (I'm one of them) who is moderating redundant all "In soviet russia", "Bewolf cluster" and other redundant memes, they are not funny anymore.
Meta-moderators seem to agree with us since there is a constant influx of mod points into my account.
There is no lack of hard AI problems that could benefit immensely from a decent AI solution. Examples abound:
1. Self driving vehicles as in the DARPA driving challenge
2. Computer vision for autonomous robots
3. Image classification systems (even for desktop apps)
4. Voice recognition systems
Numenta claims HTMs are very powerful and yet instead of attacking one of these problems either as a demo (so they can be swept up by Google in the bat of an eye) or for profit, Numenta is giving away a dev. platform with some source (with some of their secret sauce) and a stick figure recognition demo. There is also a distinct lack of HTM based projects out there on the web.
There are 2 possible explanations I can think of for this:
1. Numenta (or anyone else) hasn't figured out how to do anything useful with what it created, implying it's not as powerful as claimed.
2. Numenta is trying to profit from selling shovels to the gold miners.
At present, given the abundance of gold on the floor, I'm inclined to believe #1 is the case.
Actually just as much evidence contradicts that hypothesis. We have very specific brain areas for generating and processing verbal data (Broca and Wernicke's areas), and a very specific brain area for recognizing faces.
In defence of Hawkins, note that he does not disagree (RTA) that there are specialized regions in the brain. However, this does not imply that the brain uses a different neural mechanism for different regions. It only means that a region that receives audio input will specialize in processing sounds. It all has to do with how the input and the output fibers are connected. The cortex will rewire itself to accomodate any sensory modality. IMO, Hawkins is right in this regard. Even specialized areas of the visual cortex that show a gradation of recognition capabilities can be explained using a hierarchical system heavily dependent on feedback.
LOL. I wrote that comment in Word to spell check it, then select-all cut/paste. I had been working on a web service and got part of the documentation. pwned!
I have been thinking of this for a while, but all our brain does is run down a path to make a decision on weighted randoms and re-sort the indexes and weights based on the feedback. Kinda like the PageRanking, but more sophisticated.
For example, to 'decide' whether an object is a ball:
if(object = round){
if(sphere = perfect){
if(pattern = checkered){
random([soccerball,art][weight10,weight1])
}
}
}
And deciding on the feedback we get: (if positive weight + feedbackstrength else weight - feedbackstrength)
we do make more accurate decisions in the future (or hopefully).
Of course such database would become infinitely large and slow (currently at least) compared to our brain, just because of the technology constraints but I think you could pull it off.
Custom electronics and digital signage for your business: www.evcircuits.com
While futuristic men are out (in) being cavemen with computers that look, feel, and think (somewhat) like women; women will be going out and impregnating themselves.
After Millions of years of evolution, Nature tends converge on the low energy solution to a problem. Using nature as a reference is most likely the best starting point!
Thanks. I'll make sure that I metamod all Redundant mods for /. memes as unfair. You won't be a moderator for long.
Did you just come over from digg or something? What a tuber...
Blasphemy! To believe that a lowly monkey man created our brains a few hundred years ago!? Madness I say! And illogical too! Everyone knows that our 'souls' came into being by miraculous inception. I believe it involved a lighting strike on an Intel fabrication plant, or perhaps it was AMD (computer god rest their soul). Regardless, the monkey men are only good for distilling into basic nutrients to fuel our sacred circuit boards.
I have spoken! As for that so called 'theory of evolution', everyone knows that 64,000,000,000,000k should be enough for everyone, who says otherwise!
No he's not, go away.
"By the age of five, a child can understand spoken language, distinguish a cat from a dog, and play a game of catch."
What? my nephew is 4.5 years old and already can:
1) switch on the computer, start MAME and play video games
2) switch on the TV, insert DVDs, pause the movie and go the bathroom, resume.
3) play excellent football (soccer), doing especially impressive dribbling.
4) can read and say numbers up to 100.
5) can read letters and write a few words.
6) phone using a cell phone.
7) can tell most dinosaur species apart and name them by their scientific name.
8) sing quite a few songs and tell quite a few poems.
And it's not the only kid that can do those things...most of the children in the nursery school are at the same level, more or less.
I think the article seriously underestimates human intelligence.
I know you will not consider my lowly opinion, but perhaps it may be of help to you:
Intelligence is simply pattern matching on the whole experience of living, from day of birth, up to the current moment, with a single purpose: to increase the chances of survival of what the entity represents (which may not be the entity itself) that carries the brain.
Consciousness emerges when the brain has a sufficient model of the universe and can theorize about itself.
Perhaps the brain has developed special areas for each function, but they all work in the same principles, in my humble opinion. If you want artificial intelligence up to the level of a human, let a computer do pattern matching on what it sees, hears, touches, smells and feels, with the only purpose to increase its 'happiness'.
It's even funnier when someone takes it upon themselves to inquire about your religious beliefs and you respond peacefully that you are an atheist, they sometimes get VERY agitated...as if your mere honest, unassuming answer is an attack on them. If they are so secure in their beliefs, they shouldn't get so angry, now should they?
The basic concepts here are IT. THE technology for our century. Perhaps this implementation isn't the right recipe, but the basic ideas here can make (or destroy) entire nations.
It's always been obvious to anyone with the right background that the brain, despite it horrendous complexity, must be organized procedurally with an extremely simple pattern.
- the cortex is NEW. Nature has not had many organisms to evolve a complex pattern. It must be very simple. This is a hard reality due to the limits of evolution. Even if the latest science can't pin down how the cortex works precisely, it CAN'T require that complex a pattern to develop.
- the cortex is incredibly flexible. It can deal with virtually anything we throw at it, as long as there is not major physical damage and the input is within it's capabilities to process. (since the brain is very slow, it can't process some kinds of information, of course)
Therefore, once we work out what this pattern is, we can replicate it and build machines with capabilities approaching a human brain.
NOTE : we need specialized hardware. While the latest CPUs of this age may be quick at linear code, a neural net is both massively parallel but requires enormous interconnect bandwidth. Specialized ASICS will have to be designed, rack after rack of them for the supercomputers needed to research this.
How will this techology change the map of nations? Because, a society with working self evolving AIs could accumulate a technological edge at a prodigious rate.
Hell, even slashdot has had stories like that. Where have you been?
---- Booth was a patriot ----
I'd be more worried about them kicking our carbon-based asses: "Thou shalt not make a machine in the likeness of a human mind."
Only three things are certain; death, taxes, and apocryphal quotations - Ben Franklin.
Won't work, because concepts aren't descriptions. Read some of the philosophical and psychological literature on concepts.
Freedom is not increased by mere diminuation of government. Anarchy is freedom for the strong and slavery for the weak.
The attempt to build a computer that works like a brain is one thing that will help them learn how a brain works.