Slashdot Mirror


Neuroscientists Offer a Reality Check On Facebook's 'Typing By Brain' Project (ieee.org)

the_newsbeagle writes: Yesterday, Facebook announced that it's working on a "typing by brain" project, promising a non-invasive technology that can decode signals from the brain's speech center and translate them directly to text (see the video beginning at 1:18:00). What's more, Facebook exec Regina Dugan said, the technology will achieve a typing rate of 100 words per minute. Here, a few neuroscientists are asked: Is such a thing remotely feasible? One neuroscientist points out that his team set the current speed record for brain-typing earlier this year: They enabled a paralyzed man to type 8 words per minute, and that was using an invasive brain implant that could get high-fidelity signals from neurons. To date, all non-invasive methods that read brain signals through the scalp and skull have performed much worse. Thomas Naselaris, an assistant professor at the Medical University of South Carolina, says, "Our understanding of the way the words and their phonological and semantic attributes are encoded in brain activity is actually pretty good currently, but much of this understanding has been enabled by fMRI, which is noninvasive but very slow and not at all portable," he said. "So I think that the bottleneck will be the [optical] imaging technology," which is what Facebook's gear will be using.

58 comments

  1. Relevance by Beau1080p · · Score: 0

    This is just one of Zuckerberg's many con-schemes to try to stay relevant. Once you've grown a company that much, where do you go if you want to continue to grow your company and maintain your omnipotence?

    1. Re:Relevance by The+Real+Dr+John · · Score: 2

      Considering how much people need to correct what speech recognition software does with your spoken words, this isn't going to work. The electrical signals that get through the skull are weak and noisy. Each person is going to have different brain patterns. But it makes for a great press release and gets people talking nonsense about it.

      --
      A brain is a terrible thing to waste... Mind? That's debatable.
    2. Re:Relevance by tsqr · · Score: 1

      where do you go if you want to continue to grow your company and maintain your omnipotence?

      Heh. If your omnipotence needs to be maintained, you're not really omnipotent.

    3. Re:Relevance by Anonymous Coward · · Score: 0

      Still, I expect the output to be better than the stuff some people keyboard onto Facebook currently.

    4. Re: Relevance by Anonymous Coward · · Score: 0

      This will run in the cloud, freeing up resources and operating at the speed of light, enabling numerous synergies and disrupting the establishment.

    5. Re:Relevance by michelcolman · · Score: 1

      In other news, rocket scientists offer a reality check on the SpaceX "land rockets on barges" project. If NASA can't do it, nobody can so it's a waste of time and money to even try it.

      What's the budget of the Medical University of South Carolina? How much money does FaceBook have? Yep, thought so.

    6. Re:Relevance by The+Real+Dr+John · · Score: 1

      Oh sure, rich people are going to save the world. Ayn Rand would love your world view. If a rich person can't do it, it can't be done, right? I'm sure they will put millions of dollars into it before they realize that it won't work. But why not? I saw it in a movie once! And next, Facebook will invent warp drive and teleportation. You know, because they are rich!

      I've read some of the primary literature on doing this in people who are disabled. It is not going to be practical for regular use, and will never be faster or nearly as accurate as typing. But who knows what they may come up with in the process of trying; a cozy head warmer maybe. Or an IoT pizza ordering device for your head.

      --
      A brain is a terrible thing to waste... Mind? That's debatable.
    7. Re:Relevance by michelcolman · · Score: 1

      Would you prefer them spending their money on private jets, big mansions and wild pool parties?

      For crying out loud, if rich people want to spend their money to advance the state of the art, I applaud it. Musk has already achieved things that seemed impossible a decade ago. Landing and reusing orbital class boosters at prices even the Russians can't match, making electric cars that people actually want to buy, etcetera. And he's not the only one. I'm all for rich people spending their money that way instead of just throwing it away for their private pleasure.

    8. Re:Relevance by The+Real+Dr+John · · Score: 1

      So what is Musk going to do with his rockets? Send rich people into orbit for a hefty price tag so he can make even more money? Wow, now I'm sold on rich people doing big things. How about maybe he spend his money to cure cancer, and give the treatments away once they are available? Oh, that wouldn't make any money. OK, so he can sell his cancer cure to very rich people who can afford it. Great. Now I'm really sold on rich people doing big things.

      Look, rich people are rich because of a broken, oligarchy system that is rigged in their favor, and they don't give a shit about regular people. Their behavior proves that to be true. A true philanthropist would spend their money for the betterment of everyone, not just to make more money.

      --
      A brain is a terrible thing to waste... Mind? That's debatable.
  2. By brain? by Anonymous Coward · · Score: 0

    Is it just me, or isn't my typing this with my fingers "typing by brain"?
    Like "brake by wire" isn't really braking with a wire, just a different way of relaying the message and applying the force.

    Also, when I read "typing by brain", I couldn't help but imagine opening a skull and comically bashing a brain against a keyboard.

    1. Re:By brain? by Ihlosi · · Score: 1
      Is it just me, or isn't my typing this with my fingers "typing by brain"?

      No, it's typing with muscular peripherals that are connected to your brain via UPPNCP (universal point-to-point neural connection protocol).

      Just imagine what happens if either the peripheral is not working correctly or the UPPNCP connection is faulty or severed. Your brain may still want to type, but it can't.

    2. Re: By brain? by Anonymous Coward · · Score: 0

      Perhaps we should develop a new protocol that doesn't require serial input (one character at a time, in sequence). Something like those sloppy circles from The Arrival.

  3. One *hundred* words per minute? by Anonymous Coward · · Score: 0

    Wait a sec... most of us here can't *think* at 100WPM.

    OTOH... it's Facebook, so they're talking about Facebook-typical "content". So then yeah, that sounds feasible.

    1. Re: One *hundred* words per minute? by Anonymous Coward · · Score: 0

      I can think at 100wpm. I'm just not sure I'd want to record that stream of consciousness for shiny things mmm hungry is my laundry done posterity.

    2. Re:One *hundred* words per minute? by dwillden · · Score: 1

      Count seconds to 60. Use the traditional quasi accurate method of "one one thousand two one thousand....". You might come up a little short but that's 180 words a minute, and it's not all that fast.

      --
      I'm too lazy to compose a creative sig.
    3. Re: One *hundred* words per minute? by Ihlosi · · Score: 1
      I'm just not sure I'd want to record that stream of consciousness for shiny things mmm hungry is my laundry done posterity.

      You don't want to, but FB does. Who knows what little gems of data it can extract from that stream and then monetize ...

    4. Re:One *hundred* words per minute? by Anonymous Coward · · Score: 0

      Now multiple that by about 20. That's how many characters you're actually going to generate with your 180 words per minute. There's a reason why an accurate 90-100 words per minute is considered a pretty proficient touch-typist. To get to that point requires training and muscle memory.

      Your analysis would be correct if they did it via some method of word selection. You may only have to select 180 words, but then your character pool is now in the tens or hundreds of thousands. You would be better off using character input with predictive text.

    5. Re:One *hundred* words per minute? by tsqr · · Score: 1

      Now multiple that by about 20. That's how many characters you're actually going to generate with your 180 words per minute.

      For the purpose of calculating typing speed, a "word" is 5 characters in length, including spaces and punctuation. 180 typed words per minute is 900 characters per minute, or 15 characters per second. That's superhuman typing speed, but not all that impressive for speech.

    6. Re:One *hundred* words per minute? by TheRaven64 · · Score: 1

      Most people talk at around 150 words per minute, so presumably they're doing something approximating thinking at the same rate.

      --
      I am TheRaven on Soylent News
    7. Re:One *hundred* words per minute? by Anonymous Coward · · Score: 0

      I was specifically referencing the above text with counting one one thousand and up, which is why I stated "your 180 words per minute."

      That is going to range from 17 characters per three words (one one thousand and following space) to about 26 characters per three words (twenty-seven one thousand and following space, for instance). Not being willing to take the time to actually do an accurate count, I approximated to 20.

      To reduce the character could you could also argue that it could also be displayed as 1 1,000; 2 1,000; 3 1,000; and so on, but that was not how the argument was presented.

    8. Re:One *hundred* words per minute? by avandesande · · Score: 1

      with the things I hear people say I would guess it is actually about 1/3 of that ;)

      --
      love is just extroverted narcissism
    9. Re: One *hundred* words per minute? by Anonymous Coward · · Score: 0

      Hungry for donuts? Need detergent to get donut grease out of your favorite T-shirt?

    10. Re: One *hundred* words per minute? by Ihlosi · · Score: 1
      Hungry for donuts? Need detergent to get donut grease out of your favorite T-shirt?

      And you'll also need coffee, and the latest miracle drug to treat obesity. Hey, can we check your insulin levels while we're at it? You already gave us access to your brain, so looking into something as innocent as the level of a hormone shouldn't be an issue, right?

    11. Re:One *hundred* words per minute? by Anonymous Coward · · Score: 0

      That because thinking is not needed for speaking, hence those that don't think have the advantage here, the free resources available to them by not thinking can be used to speak faster

  4. Scientisis by 110010001000 · · Score: 2, Insightful

    Those fuddy duddy scientists know nothing. Facebook will make an APP for it. In the Cloud. VR and IoT ready.

    1. Re:Scientisis by Rudisaurus · · Score: 1

      Oh come on -- what fool modded PP as "Insightful"? It was meant to be FUNNY, people!

      --
      licet differant, aequabitur
  5. Just a few more years . . . by Anonymous Coward · · Score: 0

    Add this to fusion and autonomous cars already on the list of things that are just around the corner!

    1. Re: Just a few more years . . . by Lije+Baley · · Score: 1

      No no those cars have to be coming real soon now so I can leave the driving to them and focus on my hipsterisms.

      --
      Strange things are afoot at the Circle-K.
  6. Ok, now think about it. by Ihlosi · · Score: 2
    IoT ready.

    The T in IoT is either a) some thing very close to, or even in, your brain or b) your brain

    1. Re:Ok, now think about it. by OffaMyLawn · · Score: 1

      My CPU is a neural net processor. A learning computer.

    2. Re:Ok, now think about it. by JoeDuncan · · Score: 1

      IoT ready.

      The T in IoT is ... your brain

      I for one, welcome our new Internet of Brains (IoB) overlords!

  7. I have EEG experience and my two cents by TheOuterLinux · · Score: 4, Interesting

    From what I learned doing research, I also think 100 words per minute is extreme. You wouldn't believe the artifacts you get just from blinking or moving a leg or finger, and I had a 21 channel MITSAR and WinEEG to work with. The only way this is going to work is if Facebook has plans involving AI and quantum computing, a very dangerous combination for privacy. This is because an AI would have to get to know your brain waves on an incredibly intimate level, making encryption a joke when your brain is getting digitally fingerprinted. If what they say works, both the polygraph test and "truth serum" would be a joke. The only actual application for finding brainwave averages between people currently is to add to the "what are artifacts" knowledge and perhaps a quick and dirty diagnoses. Very rarely have I ever been able to use EEG to find correlations in research because everyone is too different and there is always some kind of confounding variable. Biofeedback projects in EEG sort of works for fun little things, but it's not the same thing as "mind reading" or 100 words per minute good. Now, I've played around with Tobii eye tracking, and that would be their best bet. In the the Linux and open source world we have a program called Dasher that may work with eye tracking to get their quota. Besides, doesn't Facebook have enough biometric data or are their government overlords hungry for more? This is why they'll never go bankrupt, as long as they have projects like this. Meanwhile, other more important research gets cut.

    1. Re:I have EEG experience and my two cents by xvan · · Score: 1

      But what about correlations between different samples of the same person. With enough training this may be feasible.

    2. Re:I have EEG experience and my two cents by Anonymous Coward · · Score: 0

      It may be feasible, but I was working on a project like this and....yeah. The problems we were running in to was sorting signal from noise. As the OP said, blinking or moving and it was basically impossible to find the brain wave from the noise. And the noise was....well, noise. It's kind of like trying to pull a cell signal out of the air in a high interference environment, but you don't get to define any sort of coding scheme to help you find your signal. You never quite know what the brain wave is going to look like and you never quite know what the noise is going to look like. We were getting to a point of trying to get funding for a proposed start up, we all looked at each other and said with the results we're getting would we be willing to throw $1000 at it, and with how unreliable our results were, we just all shook our heads and dropped it. A lot of effort wasted, but such is life.

    3. Re: I have EEG experience and my two cents by Anonymous Coward · · Score: 1

      And instead if you'd just lied a little you could've sold to FB for 1000000000$.

    4. Re:I have EEG experience and my two cents by Anonymous Coward · · Score: 0

      > WinEEG
      Running on windows? Ech, well there's your problem.

    5. Re:I have EEG experience and my two cents by Anonymous Coward · · Score: 0

      Yamn... wake me up when they solve the Binding Problem. That's the first thing you need to know well in order to understand consciousness [and, as of now, nobody has a clue].

    6. Re: I have EEG experience and my two cents by TheOuterLinux · · Score: 1

      It gets worse. We were running Window$ on iMacs. If I could at least try WINE on Linux with it, I would have, but they just bought the equipment and WinEEG needs a USB key to communicate live with the MITSAR. It would of been interesting to find out. I did look into other programs for Linux, but none are as easy to use and the compatible equipment is cheap and archaic in comparison. You can find a lot of biofeedback projects for Linux, but most of those are 2-5 channel and not 21. They do make Bluetooth EEG headsets for phones (iOS/Android) now, but they're junk and the saline solution destroys them over time. They market most of them as devices to improve your mental wellbeing by monitoring your brainwaves. You can be half asleep and get the same results as any "zen master." Fun fact why I'm thinking about it, they made a biofeedback Star Wars force toy way back during episode one or two I think. I don't know about 100 words a minute, but if you need to float a ball in a brain controlled air tube: http://usatoday30.usatoday.com.... Also, if you want to hack that toy with an Arduino: http://www.instructables.com/i...

    7. Re:I have EEG experience and my two cents by TheOuterLinux · · Score: 1

      HBI (Human Brain Indices) Database is what is used: https://bio-medical.com/hbi-hu.... WinEEG did have this as an add-on option, but the department wouldn't splurge for it, so I was stuck using experience versus whatever WinEEG was nice enough to include for cleanup, to which presents another problem. If you clean up artifacts, you have to use the same processes whether it is the same or another person. And no matter how many artifacts you can remove, time, temperature, clothing, hair style, health, etc. affects the waves. The power source (50 Hz vs 60Hz for example) and hardware also affect the waves. At no point in time is a normal human being just a "normal" slate of consciousness. Facebook would have to use a computer to fill in the blanks and that computer would have to have immense processing power to keep up, to which AI quantum computers could do. You might want to take a look at this too: http://www.pnas.org/content/11.... It's about how many (~40,000) fMRI studies could be wrong do to software miscalculations and so forth. Here's a counter-argument: https://analyticalcortex.org/2.... And, I can assure you an EEG (electric activity) is not as accurate as an fMRI (metabolic changes), though they do complement each other.

  8. Maybe its true by Anonymous Coward · · Score: 0

    As soon as I read through the article, I immediately experienced some pain in my head. Could be one of the early symptoms of their superior "technology"

  9. Unfortunate by Nidi62 · · Score: 4, Funny

    I would have had first post, but I used a prototype to type this :(

    --
    The only thing necessary for evil to triumph is for it to be pitted against a slightly greater evil
  10. Tiger Direct by gatkinso · · Score: 1

    Used to sell a brain controlled mouse, IIRC.

    --
    I am very small, utmostly microscopic.
    1. Re:Tiger Direct by __aaclcg7560 · · Score: 1

      When I worked at the Google IT help desk in 2008, a user called in to have a tech take remote control of her desktop and move the mouse on her instructions. So she called a coworker over to demonstrate a voice-controlled mouse. When the user gave instructions to move the mouse, the tech moved the mouse for her. The coworker was so amazed by this until she found out it was a prank.

  11. Not impossible by grumbel · · Score: 1

    100 words per minutes might be a stretch, but it doesn't sound all that impossible given that the speed record was set with hunt&peck typing by moving a cursor across the screen. Some fancy machine learning that could guess whole words at a time or something along the line should have no problem beating that by quite a margin. It wouldn't even need to be perfect, just close enough, to give a drastic speed up (i.e. like Tab-completion).

    See this earlier work that guessed video sequences from brain activity. Getting information in a more 'holistic' form out of the brain instead by just cursor movement seems plausible.

  12. Is anyone surprised? by Anonymous Coward · · Score: 0

    Is everyone finally beginning to understand that Silicon Valley at large is delusional, not nearly as intelligent or competent as they claim to be, and essentially just a bunch of very well funded people that never compared their teenage fantasies to the actual laws of physics? Most of what is happening there is a very expensive joke. It can't last. Their insularity and arrogance WILL relegate them to irrelevance eventually when others that are devoid of this dysfunction step up to the plate elsewhere. It's just a matter of time.

    1. Re:Is anyone surprised? by Anonymous Coward · · Score: 0

      Why would their delusions be stopped by reality, when they manufacture public opinion themselves, in the corporate media they themselves read? Also, how is silicon valley relevant today? Everybody who's anybody manufacture their own processors and rad hardened chips... China, India, Russia. Everybody knows $OTHER_COUNTRY designed electronics cannot be used for anything strategically important, but that has been evident since that hilarious thing with Exocets during Falklands War.

      The thing that puzzles me, is the undeniable fact that silicon valley is making money, despite designing all this useless centralized consumer garbage. Which makes me ask... Can it be any other way, when it is HUMANS that market, manufacture and program all of these devices?! The deception and overt control over the dataflows and fishing in the upstream are unavoidable, because of human will-to-power? And, with the power and reproductive dynamics shaping the overall trajectory of this inescapable attractor, there isn't much humans can do about it?

      But hey, i also agree that it'll probably sort itself out. All things do.

    2. Re:Is anyone surprised? by CustomSolvers2 · · Score: 1

      There have so much money and software-based anything generates so much revenue with a relevant investment that this apparent nonsense seems self-sustaining! This project, for example, is likely to not lose a dime, even to generate profits, independently upon its final outputs. After injecting a relevant amount of money, Facebook might start applying for R&D grants/prizes which will most likely earn; just this might be enough to account for all the costs during some years. Additionally, it will be very positive for the public image of Facebook as a game-changer and R&D-focused company. All the workers and managers will get lots of money, excellent experience for their CVs and lots of relevant knowledge (even in case of not reaching a proper product, working on so demanding projects is the best to get top-level expertise). Facebook might even get some further direct benefits via commercialising preliminary versions or merchandising.

      When you have enough money to invest, losing in software is virtually impossible, mainly in a place like Silicon Valley which has already an important intrinsic value (virtually anything from there gets lots of attention/free advertisement and is appealing to customers everywhere). I mean having more expenses than earnings, because in case of bringing costs of opportunity into picture too, all these jokish projects would be pure losses. But I guess that nobody cares/knows as far as the apparent profit continue flowing.

      Someone might think that people like me might be unhappy with such an unfair situation, but I do fully accept it. Note that my personal situation (as the one of most of programmers/software-companies outside a few privileged areas) is completely different than all that: no investors, no opportunities, no money flowing around, having to do everything perfectly to be systematically ignored, not having any kind of support (for most of people in the town where I am now programming isn’t even an actual occupation or cannot understand what remote work is), etc. Although I would certainly love working under better conditions, I wouldn't ever renounce to some of my current benefits (e.g., doing what I consider right without tolerating ignorant arbitrary impositions); I am also sure that most of people working on these generating-money-from-nowhere projects are systematically tolerating what I would never do. That's why I don't envy those programmers and think that this Silicon Valley apparent nonsense is likely to continue existing for a while (and, hopefully, the TV series forever! Season 4 premiere on Sunday!!).

      --
      Custom Solvers 2.0 = Alvaro Carballo Garcia = varocarbas.
  13. first thing I will type by avandesande · · Score: 1

    m y s p a c e

    --
    love is just extroverted narcissism
  14. Implants by Anonymous Coward · · Score: 0

    I think it's clear we will need implants but so what? Implants will beat carrying around a wallet and a phone everywhere you go. Upgrading will probably suck majorly, but that's the price of progress. Cyborgs are the future boy and girls and we should be happy it's cyborgs and not Terminators though maybe it will be both....

    1. Re:Implants by Anonymous Coward · · Score: 0

      I think it's clear we will need implants but so what? Implants will beat carrying around a wallet and a phone everywhere you go. Upgrading will probably suck majorly, but that's the price of progress. Cyborgs are the future boy and girls and we should be happy it's cyborgs and not Terminators though maybe it will be both....

      Implanted replacements for something as complex as a phone will never be commercially viable. Putting a box in your pocket is too much more convenient than getting surgery that there's no comparison. Even if medical tech advances to the point that they can insert the devices non invasively and have them self assemble in place, you'd still need an extended training time as your brain learns to us the new hardware... every time you want to upgrade your phone.

      An implanted communication device so you can control the phone in your pocket over a mostly industry standard BMI protocol might be viable but we have a long way to go before that's commercially viable either. I doubt it'll hapen this century.

  15. I'm using it right now by ilsaloving · · Score: 1

    I'm using it wiggle fingers right now foot itches squirrel is it lunch time yet and it works perfectly did I leave the oven on well I smell pizza i can't believe I did that 10 years ago.

  16. There appears an obvious solution here. by SuricouRaven · · Score: 1

    Invasive brain implants for everyone!

  17. Brainless by volodymyrbiryuk · · Score: 1

    They should make sure Facebook developers have a brain in the first place. Every piece software developed by FB is pure garbage. Is this some kind of lame attempt to get brainwaves data depending on what FB advertisement users are seing? Besides that BCI input devices have been around for years. He's trying so hard to be Elon Musk.

    --
    sudo rm -r -f --no-preserve-root /
  18. Re:Yeeeup by Anonymous Coward · · Score: 0

    Well until we can repeal that pesky first amendment, all the ministry-of-truthing will need to be delegated to private corporations. The fact that such a huge percentage of all human communication and information consumption occurs under the supervision of a tiny handful of megacorporations that for some reason never seem to come under anti-trust scrutiny is merely a pleasant coincidence.

  19. Shouldn't be too hard, to do. by Anonymous Coward · · Score: 0

    Facebook's users vocabulary is extremely limited. 'Urgh', 'grrr', 'Trump', 'Dirty foreigners(who Doctor my children, design my phones and most of it's apps, gave me my job back because David Somethingstein just bought our dying factory)', 'Ohh Hilary my demigod, your picture I set as my background, smiled at me[faint]', 'Dogs are people too', 'This new berry, that rodents won't even eat, will cure all cancers and raise your loved ones from dead', etc....

    1. Re:Shouldn't be too hard, to do. by Anonymous Coward · · Score: 0

      Sorry, that got away from me. I was going to use, possible, one or two word sentences. I mean come on, their favourite site is two syllables. A three word sentence? Preposterous, poppycock, Weiner schnitzels.