Forgot your password?
typodupeerror
Biotech Robotics Science

Brain Interface Lets Monkeys Control Prosthetic Limbs 208

Posted by timothy
from the what-did-you-do-at-the-lab-today-bonzo dept.
himicos was one of many readers to point out one recent success of scientists working to develop working brain-machine interfaces, writing "A team at the university of Pittsburgh has finally advanced a 2002 technology enough for use in prosthetic limbs, the targeted application all along. Training computer models to the firing patterns of the neurons in the parts of the brain that control motion, they are able to project the intentions of a monkey to a robotic arm, which follows the will of the animal. The sad thing about the articles is that the beauty of the mathematics used to create and train the models is totally ignored." Reader phpmysqldev adds a link to coverage at the BBC, and writes "This of course brings significant hope to amputees and other other people with physical disabilities." (Note that this research has been going on for quite some time.)
This discussion has been archived. No new comments can be posted.

Brain Interface Lets Monkeys Control Prosthetic Limbs

Comments Filter:
  • by oahazmatt (868057) on Thursday May 29, 2008 @08:23AM (#23585235) Journal

    Brain Interface Lets Monkeys Control Prosthetic Limbs
    And just like that, a SciFi channel original movie is conceived.
    • Re: (Score:3, Funny)

      by elrous0 (869638) *
      You reserve the studio in Bulgaria, I'll call Bruce Campbell!
      • Re: (Score:3, Funny)

        by Sponge Bath (413667)

        I'll call Bruce Campbell!

        Add Glen Campbell and make it 'Monkey Robot Overlords: The Musical!'

    • Re: (Score:2, Insightful)

      by Anonymous Coward
      I notice nobody here gives a toss about the pain and suffering, and terror, that this poor creature has gone through, and all for naught.

      If this technology ever makes it to humans, it will only be after HUMAN experiments are done. Of course, the frauds who call themselves vivisectionists will say that "We couldn't have achieved the human version without first torturing - sorry - 'experimenting' on monkeys", but the first human version will fail, guaranteed. They will be EXPERIMENTING on humans, until they f
      • by mpeskett (1221084) on Thursday May 29, 2008 @11:53AM (#23588219)
        You'd prefer they started out by sticking electrodes into humans with no idea what they were doing?

        Of course some experimentation will be needed when they move to human subjects, but a monkey's brain is similar enough to ours that they can get a starting point to experiment around, rather than working blind on a human subject.

        One other thing to note, there are no touch/pain receptors within the brain itself - people have brain surgery done while awake so the doctors can keep them talking and know they aren't accidentally removing something important. Once you've got an opening into the skull (which would be done under anaesthetic) you can poke and prod at the brain all you want without the subject feeling a thing.

        Oh, and its on the news because its interesting and something of a step forward scientifically. Quit it with the conspiracy theories please.
      • Re: (Score:3, Interesting)

        by susano_otter (123650)
        A few years ago, a baboon snatched a live human baby, tore open its skull, and ate its brain, in full view of the baby's mother. A source [ibiblio.org].

        Now, as a strict materialist, I see no reason to think that this baboon does--or should--feel any remorse for its actions. They were clearly the result of mindless evolutionary processes, just like your own feelings about animal experiments. You feel bad because your species' biological evolution compels you to feel bad. With any luck, it will also compel you to feel bet
    • ..."Robotic Arm Controls Monkey Brain."
    • Brain Interface Lets Monkeys Control Prosthetic Limbs
      And just like that, a SciFi channel original movie is conceived.
      Likewise, both will be used to hurl feces at unsuspecting people.
  • if/when we invent lightsabers, we should have the robotic limb problem solved. other than that, this should help paralyzed people move again
  • Would the OP or someone else in the community care to take a moment to explain the beauty of the math for us non math-majors?
    • by kalirion (728907) on Thursday May 29, 2008 @08:51AM (#23585575)
      How would you explain the beauty of a sunset to the blind?
      • Make them some prosthetic eyes?
        • Pff. Done already. [idtechex.com]
          • Re: (Score:3, Interesting)

            by somersault (912633)
            Didn't say it hadn't, but the colour and resolution on those things isn't going to be much use for watching a sunset :P
            • Re: (Score:3, Insightful)

              You're right. What's really sad is the number of sighted people who can but simply don't bother.
              • Yeah. I've even spent time just watching them in games like Grand Theft Auto, and a nice sunset in Uncharted (although the sun never actually goes down in that scene) - they're pretty good approximations :) The last real sunrise I went to see down at the beach was a bit of a let down, cloud in the way, and the sun was tiiiiny!
      • by dezert_fox (740322) on Thursday May 29, 2008 @09:57AM (#23586437)
        Shannon entropy has been a standard tool in data communications for a very long time--telcos use this math to make your phones work. It's effectively a way of quantifying the informational content of a signal, which can be used to determine exactly what kind of bandwidth you need in a bandwidth-limited environment. I'm uncertain what it's used for in the context of a brain-machine interface.
        Any good data communications textbook would have some nice examples in it, and actually that wikipedia article posted is very readable and informative.
    • Re: (Score:3, Insightful)

      by jellomizer (103300)
      Oh yea that will be a big hit, for the general public. Showing all the math that needs to be done. or Show a picture of a monkey with a robotic arm. Lets face it math is not a spectator sport. To observe the beuity of it you will need to sit down and look at it proove it to yourself then you can admire it. However Most people don't have the time to sit down and follow equations that most mathamatitions follow the old scheme of using Greek symbols as shortcuts to (porposly) make it very difficult to read fo
      • by Creepy (93888)
        I agree - you could have the most beautiful math equations in the world and 99.999% of the population wouldn't give a rip. That includes me, and I minored in math and may even know what they're talking about if I cared enough to read the equations.

        Monkeys with bionic limbs is another story entirely.
      • by Hognoxious (631665) on Thursday May 29, 2008 @10:05AM (#23586571) Homepage Journal

        Showing all the math that needs to be done. or Show a picture of a monkey with a robotic arm.
        It's just the same here. Consider:
        • I for one welcome our very hard mathematics doing overlords
        • I for one welcome our new bionic monkey overlords
        In Soviet Russia the same league isn't even in THEM!!!!
      • math is not a spectator sport

        Then you're doing it wrong.
        • Then please make a TV show that shows math and have people interested in it. And you need to cover all the topic not just a couple of cool little topics.

          The Nasa channel had a rather good show that covered a lot of highschool math it explained it well and really let people visualize the math... However If I had to choose that or watch Monkeys with robotic arms... Ill choose the monkeys.
      • Heck I have a Math Minor and the symbols require me to look them up...

        Yikes, that must have been a math minor program with light requirements, because all I see are summation and integral symbols, a few log's and ln's (apologies to the apostrophe Nazis), a trace and a "for all." I looks like a lot of the domain-specific stuff either has a link to a relevant article or is explained in the article itself.

        Of course, for the general public, I agree that including any math at all causes eyes to glaze over and back buttons to be clicked or channels to be changed. :)

    • by hansraj (458504) * on Thursday May 29, 2008 @09:31AM (#23586079)
      I am amazed at the number of responses being just smug and claiming how you need to do math to appreciate the beauty. Reminds me of a guy doing PhD is Chemistry about effects of certain chiral isomer of nicotine on cancer. His first response when I asked what he worked on was "You won't get it". I am a PhD student in computational geometry and I frequently have to explain my work to relatives who have no idea about geometry. When I pestered the guy that whether or not he can explain his work to a layman reflects his understanding about his work, he agreed to try. Of course I could understand the central part once he replaced the technical name of the molecule with "a chiral isomer of nicotine". I am sure it could have been further simplified as "mirror image molecule of the stuff in tobacco" in case I didn't remember what "chiral" and "nicotine" are.

      On the topic, I am not entirely sure about the exact math used in the said experiment but based on the fact that the link points to the notion of "information content", here is my guess how it should work (at least in principle). I will try just because no one else seems to. Feel free to correct me.

      The state of the neurons of the relevant area of the brain (relevant for the goal in the experiment - say pick marshmallows or open the door) could be modeled as a random variable. The first problem when trying to figure out what a certain electrical activity in brain represents would be to figure out whether you are looking at a random electrical activity (brain doing lots of background work maybe) or some order (brain trying to focus and activate the subroutine for "move hand and open door"). This difference between order and chaos is captured in a neat formula describing the entropy or the information content of the random variable. Naturally, the less the entropy the more the order. I have no idea what possibly goes on after this step.

      In any case, now coming to the "beauty" part. Of course you need an eye to appreciate beauty for the notion is quite subjective. The remarkable thing is that a simple formula captures the vague notion of "order" that we all have. The formula might not be the most beautiful thing because as I understood from the article, the log term is somewhat forced to make sure different things add up nicely. But then, one could think of this very fact (the extra log term) as a neat mathematical representation of the notion that disorder should be able to be combined with another disorder to create something bigger.

      I hope my response is better than "drop whatever you are doing and go do a PhD in math before you can understand the beauty of math".

      • I have no idea what possibly goes on after this step.

        I don't know what would go after this step either, but the one after that would be Profit!!!
      • Reminds me of a guy doing PhD is Chemistry about effects of certain chiral isomer of nicotine on cancer. His first response when I asked what he worked on was "You won't get it". I am a PhD student in computational geometry and I frequently have to explain my work to relatives who have no idea about geometry. When I pestered the guy that whether or not he can explain his work to a layman reflects his understanding about his work, he agreed to try.

        "If you can't explain it to a six year old, you don't really understand it." -- Richard Feynman*

        * Maybe, it seems this quote sometimes gets attributed to Einstein as well.

      • Yes, math is nice, but the math is totally unimportant here, in the grand scheme of things. The poster says:

        The sad thing about the articles is that the beauty of the mathematics used to create and train the models is totally ignored

        But we're talking about a technology that could give millions of kids back something akin to the legs they had blown off from landmines. People who are blind and crippled after suffering years of diabetes being able to walk again. Mothers being able to lift their kids again.

  • by crymeph0 (682581) on Thursday May 29, 2008 @08:30AM (#23585333)
    How about custom appendages? If the brain can be trained to independently control a new arm, why couldn't it learn to control a genuine Doctor Octopus suit?
    • by PachmanP (881352) on Thursday May 29, 2008 @08:48AM (#23585523)

      How about custom appendages? If the brain can be trained to independently control a new arm, why couldn't it learn to control a genuine Doctor Octopus suit?

      Speaking from experience, it is because the grant money is better. If you say you need money to research brain/machine interfaces for prothetic limbs to help disabled people, you are more likely to get it than when you say you need the research to give yourself/your_cyborg_army superhuman appendages to be used for world domination.
      • by crymeph0 (682581) on Thursday May 29, 2008 @09:31AM (#23586083)

        Fair enough, but can't this research be directly applied to my one-man-cyborg-army-of-the-apocalypse idea, even though that's not the PR angle they're going for?

        Once this technology advances to the stage where we can get genuine Darth Vader(tm) brand prosthetics after our various lightsaber mishaps, I'm just hoping that some entrepreneurial young Doctor will implant the control chips in perfectly healthy people for a fee, which you could then hook to the hardware of your choice. Of course, this may have to take place in a third world country where the FDA doesn't hold back novel ideas just because they aren't "medically necessary", or because it's an "abomination before God", or some such drivel.

      • Re: (Score:3, Insightful)

        Speaking from experience, it is because the grant money is better. If you say you need money to research brain/machine interfaces for prothetic limbs to help disabled people, you are more likely to get it than when you say you need the research to give yourself/your_cyborg_army superhuman appendages to be used for world domination.

        You have GOT to be kidding! Getting government grants to find military applications for otherwise harmless things is a staple of the defense program. If you have an answer to "How many Commies/Terrorists can it kill", you've got grant money.

        So go ahead and build your cybernetic superhumans to do your bidding, but you might have to sign a contract that says you'll do the bidding of the US government, too.

      • So you weren't going for DoD money?
    • Re: (Score:2, Insightful)

      by schmu_20mol (806069)
      Because the prosthetic is controlled by the very neurons which are normally used to control the monkeys now restrained arm. The research focused on using already 'trained' and known neurons within the brain and how to interface them with a prosthetic. Afaik, there's currently no research going on about using 'unnatural' or to the brain formerly unknown limbs.
    • by khayman80 (824400) on Thursday May 29, 2008 @10:03AM (#23586525) Homepage Journal
      I would imagine the mental map we have of our bodies has four limbs. This would mean that, for purposes of sensation, motor control and proprioception, we can't operate more than four limbs at once. Why would we evolve the ability to control limbs that we don't even have? I mean, brains are flexible, but I would guess that trying to push the "body control/sensation/proprioception" map past four limbs may have some unintended (and possibly bad) consequences.

      An alternative might be the use muscles in the face to control extra limbs. Frowning would perform one action with the prosthetics, smiling another, etc. But this would be considerably more clumsy than the intended use- replacing a limb that doesn't exist on the physical body, but does have a designated place in the brain that controls it.

      • Re: (Score:2, Funny)

        by BattleApple (956701)
        You may be on to something. I've been trying to gain control of my third leg for years, but it seems to have a mind of its own.
      • by Bones3D_mac (324952) on Thursday May 29, 2008 @03:07PM (#23591249)
        I would imagine the mental map we have of our bodies has four limbs. This would mean that, for purposes of sensation, motor control and proprioception, we can't operate more than four limbs at once. Why would we evolve the ability to control limbs that we don't even have? I mean, brains are flexible, but I would guess that trying to push the "body control/sensation/proprioception" map past four limbs may have some unintended (and possibly bad) consequences.

        Personally, I see this problem as more the case that we've only been conditioned to handle that many limbs over years of experience versus any sort of hard limit being imposed. (Not to mention it kind of runs across the grain of that whole "evolution" thing being needlessly debated...)

        There have been numerous examples demonstrating that our brains are not only highly adaptive to new situations (such as the brain redistributing certain functions to different areas to overcome damaged areas), but are also highly receptive to new forms of input from external sources (such as invasive probing of the brain to create crude brain-to-computer interfaces to control simple devices, such as an on-screen cursor.)

        The larger issue is really more of a case of creating a proper and convenient interface for cyborg-like add-ons. For example, do we necessarily have to invade the brain directly, or can we simply use existing connections by connecting jumper cables to the nerves running down the spine. And if that isn't an option, can we create or add extra, custom nerve sets to the spine and create connections to the brain that way?

        Considering all that, a "third arm", or similar contraption is probably within the realm of possibility, but it may take time to adapt to and fine tune the system before it becomes effortless (or closer to that) to use. It's actually not all that dissimilar to the steps you have to go through for setting up a decent voice recognition system.
      • I would imagine the mental map we have of our bodies has four limbs.
        Are you sure you don't have a tail still stuck somewhere in your motor cortex?

        Come to think of it, a tail would be kind of useful every once in a while.
      • by TheLink (130905) on Friday May 30, 2008 @01:16AM (#23596603) Journal
        "This would mean that, for purposes of sensation, motor control and proprioception, we can't operate more than four limbs at once."

        I'm sure that's wrong.

        We extend our mental maps to include vehicles, devices and tools that we operate on a regular basis. Believe me, some of us even feel pain when we ding our car on something. Some even feel pain if they get shot in a video game.

        The fact that many people can be trained to see with their _tongue_ means the brain is very adaptable.

        The Seeing Tongue:
        http://findarticles.com/p/articles/mi_m1200/is_9_160/ai_78681631

        Just because you start seeing with your tongue does not mean you lose sight in your eyes. So I do not believe that we are limited to controlling 4 limbs. When people use a tool they are skilled in, that tool becomes an extension of their body - and it does not even have to be physically connected to their body - ask people who do stunts with RC helicopters, or play FPS/RTS games.

        Once you practice enough, it becomes learnt and integrated into your brain, you no longer think "Ah I must press this to do X", you just think "I need to go here" and you do whatever it takes to get it done.

        A skilled typist does not think of each key stroke independently, the typist just thinks of the phrase (or sees stuff to type) and all the 8 fingers and 2 thumbs get it done. So controlling more than 4 limbs shouldn't be a huge problem.

        However, just like when you concentrate on something a lot, say drawing an intricate design, you may lose awareness of what's going on with your little toe (until something significant happens to it, or even is about to happen to it - incoming object via peripheral vision - in which case the rest of your brain brings it to your attention).
    • I propose we go a step further: forget real world appendages entirely. Lets go virtual appendages. If we can figure out how to translate thoughts into movement, assumably we could disable the actual arm's ability to move and feel with anaesthetic or something. All we need then is some sort of method for communicating sensory data back into the brain from the computer. Obviously that's not as easy done as said, but still... I hope it's possible.

      One step closer to being able to shed this shitty world and move
  • by utnapistim (931738) <dan...barbus@@@gmail...com> on Thursday May 29, 2008 @08:33AM (#23585369) Homepage
    So ... I realize that this will ultimately be adapted to humans, but could it be adapted to something else?

    Specifically, I'm thinking of adapting a laser prosthetic arm, to be used by the poor, armless sharks ...

    It's just an idea ...
  • This of course brings significant hope to amputees and other other Mad Scientists
    Fixed that for you.
  • by elrous0 (869638) * on Thursday May 29, 2008 @08:36AM (#23585405)
    I've got 1,000 of these smelly bastards sitting in a room full of typewriters, and NOT ONE of them has produced the works of Shakespeare yet.
  • That's nothing, I know tons of girls like Rogue, that can steal your powers by touching you.
  • by Paul Rose (771894) on Thursday May 29, 2008 @08:50AM (#23585557)
    >>This of course brings significant hope to amputees
    As long as they don't mind carrying a monkey to control their prosthetic arm...
  • that my (special) hands can work for me while I am on a vacation?
  • by Ukab the Great (87152) on Thursday May 29, 2008 @08:52AM (#23585583)
    Now the infinite number of monkeys will only need to *think* about Hamlet.
  • Monkeys, mind-control, robots, maths and electronics

    -- just what is this doing on Slashdot?
  • Monkey's opinion (Score:4, Insightful)

    by nategoose (1004564) on Thursday May 29, 2008 @08:59AM (#23585679)
    The monkey in the pictures had his own arms restrained within tubes so that he/she would be forced to use the mechanical arm in order to get the marshmallow, and the mechanical arm isn't oriented so that the monkey could possibly mistake it for his/her own arm. I can't help but wonder what the monkey's opinion of all this is. It's got to be more than a little confusing.
  • Almost (Score:3, Interesting)

    by speroni (1258316) on Thursday May 29, 2008 @08:59AM (#23585685) Homepage
    Almost in time for our war with largest incident of severed limbs due to IED's.

    I knew a guy in college who was working in this field. He went on to do master's work at Cornell. Incidentally he had no arms.

    This will be great to improve the standard of living for many of the returning soldiers.
    • Re: (Score:3, Interesting)

      by pizzach (1011925)

      This will be great to improve the standard of living for many of the returning soldiers.

      You would be surprised how people adapt. For many amputees this is a non-issue, and they move on. The key is time and the correct mental attitude.

      I have a prostetic leg, but I like my crutches. I'm agile on my crutches. I can do interesting things on my crutches I can't with a real leg. If I had to choose between my artificial leg and crutches, there is a good chance I would choose my crutches.

      If you look at a person who has an amputated arm, if they go for a prosthesis it is often "the hook." I

      • Tell me about it. My dad lost both his hands when he was a kid. He doesn't bother with those fake arms with hooks on them. He has had a couple of sets made up over the years, but they were never good enough. Now he's 50-ish and the most complicated artificial limb he uses is a pen, and that's only when he's typing. Oh, and he's a very successful software developer.
  • by cruff (171569) on Thursday May 29, 2008 @09:03AM (#23585717) Homepage
    Don't forget to always mount a scratch monkey.
  • I'm hardly an animal rights advocate, but has anyone stopped to ask what sort of ethics has us cracking open a monkey's head to perform these experiments?
  • by JoeD (12073) on Thursday May 29, 2008 @09:08AM (#23585775) Homepage
    Get back to me when they can use the robotic arm to fling poo.
    • I'm wondering when the monkeys will learn to use their new arm to, you know, -ahem- spank the monkey. (poor things ... locked alone in cages ... arms immobilized ... a monkey's gotta do SOMETHING to relieve the er, boredom, right?)

      On a separate note, when can I get my cyborg-enhanced trunkmonkey> [youtube.com]?
  • OMG Old! (Score:2, Interesting)

    by ggalvao (1000487)
    Miguel Nicolelis is doing this kind of job and seems to be much more advanced. http://www.thinkartificial.org/machine-interfaces/monkey-brain-makes-robot-walk/ [thinkartificial.org] He actually made a monkey in the US control a robot in Japan by walking on a treadmill. The monkey had a screen showing the robot. After realizing that she (the monkey) could actually move the robot by thinking, she developed in her brain something that enabled her to control the robot and not have to walk herself. Thus, she could earn the rewards
  • How long until one of these monkeys kills the scientists with his robotic arm, in retaliation for them removing his perfectly good arm?
  • by RevWaldo (1186281)
    Back in the early 80s there was major buzz about using computers to restore movement to people paralyzed by spinal injuries. In a nutshell, a computer would send properly sequenced jolts to the person's leg muscles, enabling them to walk. In tests this more or less worked. The electronics at the time were too big to make it practical but the hope was that in the future (now) computers would be portable and powerful enough to do the job. I recall a number of hopeful reports on "60 Minutes" regarding this res
    • Re: (Score:3, Informative)

      by Molochi (555357)
      As I recall, direct electrical stimulation, eventually killed the nuerons. Though I don't know why they couldn't eventually have a mechanical-to-biological interface that duplicated the natural one non destructiveness.
      • Re: (Score:3, Informative)

        by smellsofbikes (890263)
        >Though I don't know why they couldn't eventually have a mechanical-to-biological interface that duplicated the natural one non destructiveness.

        That's a difficult engineering problem because it's a complicated chemical process. Nerves talk along their length by depolarization, which is essentially an electrochemical process. A nerve pumps sodium and potassium ions in opposite directions across its cell membrane to form a gradient -- think potential energy, like an anvil sitting on a table -- and when t
  • Clumsy movements at best. The monkey grabs the marshmallow by moving its head instead of really using its prosthesis. It looks like it has only one degree of freedom. Still, a good achievement but nowhere near what is needed for a tree cyborg body :-)
  • Phase two will end up something like this: http://www.theonion.com/content/node/39133 [theonion.com]
  • I think that if I had a prosthetic limb I'd be very wary of letting monkeys control it.
  • Quick! Attach one to a dog so he can finally make a fist!!!
  • This is "old" news (Score:2, Interesting)

    by ittybad (896498)
    I saw this technology on a video on either TLC or Discovery SEVERAL years ago. The monkey could move a robotic arm with its brain waves. Old news. On the same episode, they showed a fella moving a cursor on a computer screen with the same technique. Also cool, on that episode, was a prosthetic leg for a guy who had his amputated above the knee. They bolted a titanium socket into his femur that protruded out of the bottom of his "nub" that could "jack" into the prosthetic knee and leg. He could, in some fash
  • by rdmiller3 (29465) on Thursday May 29, 2008 @01:42PM (#23590055) Journal

    The really cool thing that they're totally missing is that prosthetic limbs aren't limited to replacements.

    Research has shown that the brain has the ability to handle additional limbs and/or senses. So if an amputee can learn to control a replacement arm, then a normal person could also learn to control an extra pair of arms. The neat thing is that the brain would just adapt to it and it would seem natural.

  • William Gibbons' Cyber-Simian
  • The Real Sad Thing (Score:4, Informative)

    by DynaSoar (714234) on Thursday May 29, 2008 @03:58PM (#23592055) Journal
    "The sad thing about the articles is that the beauty of the mathematics used to create and train the models is totally ignored."

    The sadder thing is that the discovery of response patterns of amputated limbs being mapped to other parts of the body is totally ignored.

    A man had his arm removed. A psychiatrist attending happened to note that the man claimed to "feel" things in his missing hand when other parts of his body were touched. After careful mapping, three different response maps were found -- one each on his arm, chest and back. Each was so sensitive that individual fingers could be stimulated and he could correctly tell which.

    This major discovery in neural plasticity makes it totally unnecessary to try to decode signals from electrode either drilled through the skull, or else placed on the surface and reading signals though the scalp, skull and dura mater, which reduces the signal by 3 orders of magnitude. Either way, these signals require some massive processing because a significant command/response signal (ie. an electrical response representing a single Hebbian cellular assembly that can be clearly decoded to an intent as stated in the article) comes from 0.3% to 3% of the neurons in the region being detected, the vast majority of the signal needing rejection as false positive or noise. Using the mapped response regions allows for signal analysis based on EMG patterns that are not expected at all in the area under the electrodes, making detection and analysis trivial.

    TFA and most such research is not about giving amputees mobility. It is about decoding and using neural signals. If it were about the former, easier ways would have been used and the job already accomplished. It is about the latter because such things make more news, get more recognition, and therefore result in more grant application success.

    The resulting technology will only be applied to prosthetics as a secondary result. Its primary use will be in such as hands-off controls for fighter pilots (see Clint Eastwood's "Firefox" for your obligatory Slashdot sci-fi/movie reference), tank crews and mobile missile launchers. Maybe this is the saddest part of all, but ignoring a more certain path to success as far as prosthetics is a sad piece.

    Also sad, with a touch of irony, is the fact that the weaponry applications will be untenable because of the heuristic nature of neural processing -- getting it close but error prone will be fast, getting it right will be no faster or require less effort than hand operated controls. The slow speed and so the ability to use real-time perceptual feedback with prosthetics will make that far more successful. It remains to be seen whether after the war applications fail the research continues (ie. there is adequate funding offered) with respect to prosthetics. If someone like the US Veterans Administration picks it up when DARPA drops it, it might. I'm not hopeful.

    The portion of the above that's assertion or opinion is based on the same professional experience as the portion that's not. That experience includes development of some of the "beautiful" maths decried as being ignored. Having been prosthetic-wrist deep in the research and from both directions, I find that a minor point to consider as "sad".
  • I don't want to go all PETA or anything, I love food animals and the way their meat tastes, but this is just exceedingly assinine:

    "The sad thing about the articles is that the beauty of the mathematics used to create and train the models is totally ignored."

    I would have thought the sad part of the article is that we're still experimenting on live animals, presumably with some sort of horrible animal torture going on. Yes, there are tremendous benefits from this research. Yes, there is also a cost. And

"Out of register space (ugh)" -- vi

Working...