Slashdot Mirror


New Device Could Greatly Improve Speech and Image Recognition

jan_jes writes: Scientists have successfully demonstrated pattern recognition using a magnonic holographic memory device, a development that could greatly improve speech and image recognition hardware. The researchers built a prototype eight-terminal device consisting of a magnetic matrix with micro-antennas to excite and detect the spin waves. The micro-antennas allow the researchers to generate and recognize any input phase pattern, a big advantage over existing practices. It takes about 100 nanoseconds for recognition, which is the time required for spin waves to propagate and to create the interference pattern. The main challenge associated with magnonic holographic memory is the scaling of the operational wavelength, which requires the development of sub-micrometer scale elements for spin wave generation and detection.

67 comments

  1. Car analogy? by sinij · · Score: 3, Funny

    Could someone please explain this with a car analogy?

    1. Re:Car analogy? by gstoddart · · Score: 4, Funny

      Spinners, a big antenna, and fuzzy dice make for one bitchin' ride.

      Beyond that, I got nothing.

      --
      Lost at C:>. Found at C.
    2. Re:Car analogy? by Ann+Coulter · · Score: 1

      We already have this for accident recognition. Whenever there is a grisly accident scene on the side of a highway, everyone driving past it will spin their heads and look.

    3. Re:Car analogy? by WarJolt · · Score: 1

      When it's installed in a google car it will only be a minor accident.

    4. Re:Car analogy? by BaronAaron · · Score: 1

      If the traditional way of doing pattern recognition was a 1 stroke lawnmower engine, this new way would be a V8.

    5. Re:Car analogy? by Rob+Riggs · · Score: 1

      This is what will eventually form the basis of the speech and image processing cores in a positronic brain. Shortly after these were developed humans became extinct -- along with their cars.

      --
      the growth in cynicism and rebellion has not been without cause
    6. Re:Car analogy? by JazzLad · · Score: 1

      Now can we hear from an engineer that can explain how a 1-stroke engine works?

      --
      "If you have nothing to hide, you have nothing to fear." - Every fascist, ever
    7. Re:Car analogy? by sycodon · · Score: 1

      Sounds kinda like a Holodeck or the Matrix.

      Either way, I hope a hot redhead is involved.

      --
      When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
    8. Re:Car analogy? by daniel23 · · Score: 1

      You may remember the bit in The Hitchikers Guide about London based designers driving their Porsche against a tree with their leather jacket strapped at the front of the car to give it the perfect pattern of lines and that air of being-used-fullness.
      TFA describes what is the analogy of doing this with 1000 Porsches on the same leather jacket and later read the license plates of each of them within 100 nanoseconds from the scratches in the jacket.

      --
      605413? Yes, it's a prime.
    9. Re:Car analogy? by Impy+the+Impiuos+Imp · · Score: 4, Funny

      It's a cannon.

      --
      (-1: Post disagrees with my already-settled worldview) is not a valid mod option.
    10. Re:Car analogy? by fyngyrz · · Score: 2

      I guess you haven't tried to actually use a Google product from the inside. Fundamentally broken, obvious and repeatable bugs have gone unfixed for years, but as they tell us: "they're working on it." (cough[Shopping]cough)

      If it's in a Google car, they'll claim it isn't evil, while being really underhanded (cough[IP rights]cough), but it won't work right (cough[Shopping]cough), and just as you you commit a significant amount of resources to it, they'll either discontinue it (cough[cough]cough) or sideline it. Or never, ever add the features that would make it something actually reasonable (cough[Gmail]cough) Or simply blow out the decent features (cough[Maps]cough) Or never bother to bring it to a level of performance that is even moderately reasonable (cough[Google+]cough)

      Unless it never becomes popular. In that case, it might hang around forever. But still under-performing / broken / evil, etc.

      No, I'm not bitter. I love when a company wastes my time as if it's worth nothing. Finally I realized that trying to work with Google was making my time worth nothing. So in a way, they had the right idea from the start.

      The only car analogy I can come up with is the insufficiently Humvees the government gave our soldiers to drive over IEDs in.

      --
      I've fallen off your lawn, and I can't get up.
    11. Re: Car analogy? by Anonymous Coward · · Score: 0

      That's a pretty bad cough you got, there. Have you gotten that checked out? You might have cancer... in which case might I suggest a brief but illustrious career cooking meth in the desert?

    12. Re:Car analogy? by dsmatthews9379 · · Score: 1

      It is like a seven seater with a door for each passenger and everyone gets to sit up front to control the vehicle at the same time while somehow causing it to get to it's destination instantly without any individual passenger know where it was going, but with everyone happy with the outcome.

    13. Re:Car analogy? by Maow · · Score: 1

      Spinners, a big antenna, and fuzzy dice make for one bitchin' ride.

      Beyond that, I got nothing.

      I think this is the truck nuts to your pimped-out ride.

    14. Re: Car analogy? by fyngyrz · · Score: 1

      It's just from breathing Google's hot air for too long. Don't worry, I've quit.

      --
      I've fallen off your lawn, and I can't get up.
  2. I understood some of those words by Anonymous Coward · · Score: 5, Funny

    It seems like the kind of thing a random science-word generator would produce.

    1. Re:I understood some of those words by orasio · · Score: 4, Insightful

      This is news for nerds.
      It's a pattern detection strategy that relies on generating waves with input data, interweaving them physically, and using arrays of antennas to detect patterns.
      That's from the first couple of paragraphs.
      I don't know a lot of physics, but I am a nerd, and I like this kind of thing, so I can learn about cool stuff.
      If you don't care about it, you can look at other stories that talk about tesla and bill gates and whatever else. Posting is not mandatory.

    2. Re:I understood some of those words by MobyDisk · · Score: 4, Insightful

      I would come here more often if orasio wrote the summaries.

      The problem with the summary is that it assumes the reader is already familiar with the device. Your summary does not suffer from that problem. For instance "prototype eight-terminal device consisting of a magnetic matrix with micro-antennas to excite and detect the spin waves." WHAT spin waves? What is a terminal in this context and why is the a key thing in the summary? The summary already presupposes too much, even for a technical news site.

      On the flip side, it would be nice if you didn't also insult the person who asked for clarification. The summary is indeed confusing.

      +1 for insightful explanation.
      -1 for being an asshat about it.

    3. Re:I understood some of those words by Sardaukar86 · · Score: 3, Insightful

      If you don't care about it, you can look at other stories that talk about tesla and bill gates and whatever else. Posting is not mandatory.

      I'm not sure his point was that he didn't care about it.

      I also found the summary fairly opaque, although that is likely a reflection of my minimal understanding of math and physics. The editors usually provide summaries of complex topics that are a little more approachable for the layman but I suppose I could always flout the law and RTFA.

      --
      ..Mullah or Pope, Preacher or Poet, who was it wrote: "Give any one species too much rope and they'll fuck it up"?
    4. Re:I understood some of those words by Anonymous Coward · · Score: 0

      I would come here more often if orasio wrote the summaries.

      The problem with the summary is that it assumes the reader is already familiar with the device. Your summary does not suffer from that problem. For instance "prototype eight-terminal device consisting of a magnetic matrix with micro-antennas to excite and detect the spin waves." WHAT spin waves? What is a terminal in this context and why is the a key thing in the summary? The summary already presupposes too much, even for a technical news site.

      On the flip side, it would be nice if you didn't also insult the person who asked for clarification. The summary is indeed confusing.

      +1 for insightful explanation.
      -1 for being an asshat about it.

      Spin waves are collective oscillations of spins in magnetic materials. Also spin wave devices are compatible with conventional electronic devices and can be integrated within a chip.

  3. April Fool's by Anonymous Coward · · Score: 0

    Sorry, I got confused on the date.

  4. Huh? by chispito · · Score: 1

    Does the summary consist entirely of real words?

    --
    The Daddy casts sleep on the Baby. The Baby resists!
    1. Re:Huh? by pushing-robot · · Score: 4, Funny

      Don't worry, scientists are working on a device that can recognize them.

      --
      How can I believe you when you tell me what I don't want to hear?
    2. Re:Huh? by Anonymous Coward · · Score: 0

      Fuck it, they're going to 8 blades, basically.

    3. Re:Huh? by gstoddart · · Score: 1, Informative

      Well, a Google search for "magonic" yields an on-line branding company, but no actual word.

      The rest are words, but I can't say I understand them as combined.

      Maybe this is a viral marketing campaign?

      --
      Lost at C:>. Found at C.
    4. Re:Huh? by gstoddart · · Score: 4, Informative

      Nope, stupid human can't type ... magnonic is apparently a real thing.

      --
      Lost at C:>. Found at C.
    5. Re:Huh? by SwingKing · · Score: 3, Funny

      Looked at that page, which lead me to the SpinWaves page, which had the text: "The simplest way of understanding spin waves is to consider the Hamiltonian {H} for the Heisenberg ferromagnet:" at which point my head exploded and I went back to watching Star Trek reruns. At least there the technobabble make sense...

    6. Re:Huh? by ClickOnThis · · Score: 4, Insightful

      If I could explain it in 30 seconds, it wouldn't be worth a Nobel Prize.
      -- Richard Feynman, responding to a reporter's question, after he won the Nobel Prize

      Simplicity is good, but not always attainable.

      --
      If it weren't for deadlines, nothing would be late.
  5. Hmmm ... by gstoddart · · Score: 2

    The researchers built a prototype eight-terminal device consisting of a magnetic matrix with micro-antennas to excite and detect the spin waves. The micro-antennas allow the researchers to generate and recognize any input phase pattern

    Resulting in improved leveraging of synergies and a minty fresh taste.

    Honestly, I hope that makes sense to someone, because it sounds like computer generated gibberish to me. :-P

    --
    Lost at C:>. Found at C.
    1. Re: Hmmm ... by Anonymous Coward · · Score: 0

      i tend to agree until i read wikipedia. small chance it is not bs.

  6. We have a winner... by jeffb+(2.718) · · Score: 4, Funny

    ...for this year's "Science or Star Trek Technobabble?" championship!

    1. Re:We have a winner... by ArcadeMan · · Score: 1

      Captain Janeway: Time travel. Since my first day on the job as a Starfleet captain I swore I'd never let myself get caught in one of these godforsaken paradoxes - the future is the past, the past is the future.. it all gives me a headache.

  7. Parallel pattern matching... by skelly33 · · Score: 1

    ... I don't see how this would be an improvement over replicating the same structure in silicon with a comparator per RAM bit with as many inputs as there are bits. Compare 8 bits or a thousand bits in a single compare operation for a "pattern" match and a giant AND gate for a single 1/0 match/no match result by supplying all the input data at once....

    1. Re:Parallel pattern matching... by omnichad · · Score: 1

      I could be wrong (can't make much sense of it either), but it may scale up exponentially rather than linearly as opposed to traditional circuits. I don't really see any proof that this is true, other than they highlighted how this would somehow be an improvement.

  8. Confusing article by omnichad · · Score: 2

    The only thing I can gather from the article is that this enables a massively parallel comparator. And then somehow that translates to someday faster pattern recognition for speech / image. Very scarce on details.

    1. Re:Confusing article by fche · · Score: 1

      ... it better be massively parallel if it is to have an advantage over a software emulation of same.

  9. New device by Anonymous Coward · · Score: 0

    > magnetic matrix with micro-antennas to excite and detect the spin waves

    Uh-huh.

    You don't say.

    Oh REALLY.

    I got some excited spin waves, IF YOU KNOW WHAT I'M SAYING

  10. SCIgen? by Anonymous Coward · · Score: 0

    The summary reads like it was written by the automatic computer science research paper generator.

  11. Retroencabulator-esque by Anonymous Coward · · Score: 0

    This invention is all well and good, but how does it correct for sinusoidal deplenaration?

    1. Re: Retroencabulator-esque by Anonymous Coward · · Score: 0

      you mean tangential holistic trasformations ?

    2. Re:Retroencabulator-esque by publiclurker · · Score: 1

      Yes, by using Heisenberg compensators in the jefferies tubes.

  12. Dear Aunt by VorpalRodent · · Score: 1

    But can it do better than: "Dear Aunt, let's set so double the killer delete select all."?

    --
    Take it to the limit, everybody to the limit, come on, everybody fhqwhgads.
    1. Re:Dear Aunt by itzly · · Score: 1

      That was speech wreckognition.

  13. Miracles, yo by wcrowe · · Score: 3, Funny

    After reading that summary I feel like a juggalo. "...F*cking magnonics, how do they work?.."

    --
    Proverbs 21:19
    1. Re: Miracles, yo by Anonymous Coward · · Score: 0

      if wikipedia is not a con, it has something to do with magnetic spin and change of that.

      given the core spin tomography thing, i tend to believe there is some substance in this story. at least it is a plausivle lie.

    2. Re: Miracles, yo by H0p313ss · · Score: 1

      "Any sufficiently advanced technology is indistinguishable from magic." -- Arthur C. Clarke

      --
      XML is a known as a key material required to create SMD: Software of Mass Destruction
    3. Re:Miracles, yo by H0p313ss · · Score: 1

      After reading that summary I feel like a juggalo. "...F*cking magnonics, how do they work?.."

      Same... but I'm sure if the operation of a CPU was explained at that level of detail it would be equally opaque.

      --
      XML is a known as a key material required to create SMD: Software of Mass Destruction
  14. Well played, PR team by jfengel · · Score: 2

    Most of the time I gripe about press releases that massively overpromise, and don't contain enough real information to figure out what was actually done.

    In this case they at least put the word "could" rather than "will" in the headline. And while the barrage of jargon that followed is incomprehensible to me, it's at least pretty clear that it's real work rather than science-by-press-release.

    Now I'd appreciate it if somebody would come along and dumb it down to my level, which is still considerably higher than the fourth-grade education they usually target. So, in all seriousness: thanks to the PR team.

    1. Re:Well played, PR team by Anonymous Coward · · Score: 0

      Ok Goldilocks lol

  15. Better summary by Anonymous Coward · · Score: 1

    Article is less confusing than summary:

    "The researchers built a prototype eight-terminal device consisting of a magnetic matrix with micro-antennas to excite and detect the spin waves. Experimental data they collected for several magnonic matrixes show unique output signatures correspond to specific phase patterns. The microantennas allow the researchers to generate and recognize any input phase pattern, a big advantage over existing practices. ...
    The most appealing property of this approach is that all of the input ports operate in parallel. It takes the same amount of time to recognize patterns (numbers) from 0 to 999, and from 0 to 10,000,000. Potentially, magnonic holographic devices can be fundamentally more efficient than conventional digital circuits. ...
    The main challenge associated with magnonic holographic memory is the scaling of the operational wavelength, which requires the development of sub-micrometer scale elements for spin wave generation and detection."

    If I understand correctly it's something similar to MIMO only on much smaller scale.

  16. Back to the analog future by jtara · · Score: 3, Insightful

    It's a pattern detection strategy that relies on generating waves with input data, interweaving them physically, and using arrays of antennas to detect patterns.

    So, it's an analog computer.

    1. Re:Back to the analog future by ClickOnThis · · Score: 1

      It's a pattern detection strategy that relies on generating waves with input data, interweaving them physically, and using arrays of antennas to detect patterns.

      So, it's an analog computer.

      Perhaps more like a D-to-A-to-D computer.

      --
      If it weren't for deadlines, nothing would be late.
    2. Re: Back to the analog future by Anonymous Coward · · Score: 0

      A DAD computer? I thought those were only good for generating terrible jokes.

  17. Just invest in our patent... by Anonymous Coward · · Score: 0

    and don't ask questions about how it works

  18. Yah but by JustNiz · · Score: 2

    I tried this out in the lab but it melted my interocitor.

  19. Long story short: It is a vibrator! by Anonymous Coward · · Score: 0

    Long story short: It is a vibrator! At least that is what I could glean from the post :-P

    OK, it sounds like really cool stuff...just, the terms used for it are out of my vocabulary at this point. Give it a few years and this will be regular words. Just like "RAM" was not a commonly used term 70 years ago...and it is now.

  20. Nope. by astro · · Score: 1

    I am just going to straight call BS here. Go RTFA and look at the "figures". This is some straight made-up stuff. I wonder if there is a purpose, such as exposing the garbage you can get published in accepted scientific venues. The article is complete Quatsch.

  21. XKCD Explanation? by marciot · · Score: 1

    I need an XKCD to explain this to me. Perhaps an entry for Randall's new book, "Thing Explainer"?

    1. Re:XKCD Explanation? by narcc · · Score: 1

      Just make up any old nonsense. It's what he does most of the time.

  22. Spin Waves? by Anonymous Coward · · Score: 1

    Aren't "spin waves" what Foxnews generates?

  23. Ok I'll try: by tomxor · · Score: 4, Informative

    From what i can quickly gather from the article:

    This is all based on magnonics, which in short - is the use of magnetic spin for binary storage and or logic. This device focuses on the later...

    It does this by constructing a matrix of magnetic nodes that are effectively interconnected to neighbours (moor?) via spatial magnetic-spin sensitivity, these interconnects form the dynamic logic processing ability of the matrix.

    I think that this is somewhat like a (soft) convolutional artificial neural network for image recognition, these are constructed out of a 2d or 3d matrix of nodes with weighted interconnects in a moor-neighbourhood arrangement. The difference here i guess is that a) it's done with magnetic spin (i really have no idea why this is an advantage, maybe i'm all wrong about this) and b) being an application specific piece of hardware each node works in parallel (this is trumped as the primary reason for the speed potential in the article).

    ... Big disclaimer: I am massively speculating because the use case is not made super clear.

    1. Re:Ok I'll try: by knarfling · · Score: 2

      From what i can quickly gather from the article:

      This is all based on magnonics, which in short - is the use of magnetic spin for binary storage and or logic. This device focuses on the later...

      From what I could tell from the article, it appears to focus on both. The device allows them to quickly create and store a pattern. It then allows another pattern to be created and quickly compare the patterns.

      It does this by constructing a matrix of magnetic nodes that are effectively interconnected to neighbours (moor?) via spatial magnetic-spin sensitivity, these interconnects form the dynamic logic processing ability of the matrix.

      I think that this is somewhat like a (soft) convolutional artificial neural network for image recognition, these are constructed out of a 2d or 3d matrix of nodes with weighted interconnects in a moor-neighbourhood arrangement. The difference here i guess is that a) it's done with magnetic spin (i really have no idea why this is an advantage, maybe i'm all wrong about this) and b) being an application specific piece of hardware each node works in parallel (this is trumped as the primary reason for the speed potential in the article).

      ... Big disclaimer: I am massively speculating because the use case is not made super clear.

      From what I could tell, the advantage of the magnetic spin is that with an 8 terminal node, it can quickly create a matrix of 1,000 bits of data. It can then compare that matrix with a stored matrix. With several nodes working in parallel, it takes the same time to compare 1,000 bits of data as 10,000,000. The potential (and right now, only potential) is that a computing device with this hardware integrated in could compare an image with a stored image much faster than conventional circuits could make the comparison and result in a better matching algorithm.

      --
      Great civilizations have lived and died on false theories. Don't mess up mine with a few facts.
    2. Re:Ok I'll try: by TeknoHog · · Score: 1

      It does this by constructing a matrix of magnetic nodes that are effectively interconnected to neighbours (moor?) via spatial magnetic-spin sensitivity, these interconnects form the dynamic logic processing ability of the matrix.

      Unfortunately, nobody can be told what the matrix is. You have to see it for yourself.

      --
      Escher was the first MC and Giger invented the HR department.
  24. Storage for quantum computer ? by Anonymous Coward · · Score: 0

    Magnonic holographic memory sounds like the ideal storage peripheral for D-Wave Two quantum computers.
    Who gets to write the device driver for it?

  25. Where is the video? by imnotanumber · · Score: 1
    Now we only need the corresponding video.

    I hope it can rival: https://www.youtube.com/watch?...

    From the summary, it looks promising.

  26. Have they tried reversing the polarity? by Michael+Woodhams · · Score: 1

    (Sorry, somebody had to ask.)

    --
    Quattuor res in hoc mundo sanctae sunt: libri, liberi, libertas et liberalitas.
  27. The HAL-9000 uses holographic memory... by Anonymous Coward · · Score: 0

    ...so chronological erasures would not work.