Become a fan of Slashdot on Facebook

 


Forgot your password?
Close
typodupeerror
×
The Military Science

DARPA Testing Numenta's Brain Tech 52

Posted by CowboyNeal from the scan-me dept.
lousyd writes "CNN Money reports that DARPA and the National Geospatial-Intelligence Agency have given $4.9 million to Lockheed Martin to develop an image recognition system that will be used to scan satellite images and photographs for familiar objects. Called Object Recognition via Brain-Inspired Technology (ORBIT), the system will fuse commercial airborne EO and LIDAR sensor data into a three-dimensional, photo-realistic model of the landscape. The brains of the system, so to speak, will be Numenta's Hierarchical Temporal Memory technology, modeled on the technology growing inside human heads. The system is expected to increase image analysts' productivity by 100 times."
This discussion has been archived. No new comments can be posted.

DARPA Testing Numenta's Brain Tech More

DARPA Testing Numenta's Brain Tech

Comments Filter:
  • to start SkyNet.

  • ...and just get someone to fly around in a jet doing this? Last time I checked the average person had a brain...why do we need to spend so much cash to make a new one!

    • Re: (Score:2)

      by Fizzl ( 209397 )
      They can probably build a more accessible interface for the image analysts to this system than to your average jet fighter pilot.

    • Re:So couldn't we save the $4.9 Million (Score:5, Insightful)

      by UncleTogie ( 1004853 ) * on Thursday October 11, 2007 @11:29PM (#20949701) Homepage Journal

      ...and just get someone to fly around in a jet doing this?

      Might want to check the price of a new long-range jet, the fuel to run it, and the pilot's salary.

      Last time I checked the average person had a brain...

      ...

      Either you haven't checked in a while, or you live in Akademgorodok... [wikipedia.org]

      why do we need to spend so much cash to make a new one!

      Repeat after me.... "Research and Development is a good thing!"

    • because Jets are expensive

      they get shot down more than satelittes

      and because this is the american military we're talking about

    • ...and just get someone to fly around in a jet doing this? Last time I checked the average person had a brain...why do we need to spend so much cash to make a new one!

      Problems:

      • A single "jet" alone costs more than $4.9 million, let alone one that would operate at the necessary altitude and speeds required. (What, you don't think certain countries wouldn't want to shoot 'em down?)
      • You still have to pay for the salary of pilots to fly the plane, their training, the salaries of the maintenance p
  • it doesn't half sound like some kind of fancy porn detector...

  • Not really new.. (Score:4, Informative)

    by wanax ( 46819 ) on Thursday October 11, 2007 @11:30PM (#20949711)
    While loaded with buzzwords, this really involves nothing that's really new. The HTM is just a rehash of Adaptive Resonance Theory [wikipedia.org]
    And applications like this aren't exactly new (this link downloads a .ps.gz file). [bu.edu]

    Although it is certainly a major engineering challenge to get this type of classification to work over multiple modalities of data in any coherent way, as far as I can tell this project doesn't represent any breakthrough in approach or capability.

    • Re: (Score:2)

      by QuantumG ( 50515 )
      Hmm, engineer who's book I've read, or random guy on Slashdot.. which should I believe. Such a hard decision.

      • No need to believe... (Score:4, Informative)

        by wanax ( 46819 ) on Friday October 12, 2007 @12:31AM (#20949941)
        The good news is that this is all math! There's no need to believe anything one way or another! Sorta exciting huh? You can go and examine all the ART algorithms (I linked wikipedia because it has the PDFs linked.. did you notice? But here's Grossberg's homepage [bu.edu], just in case), and you can go read about HTM. According to Hawkins, HTM has some magical, er I mean, proprietary, component that separates it from ART. I've seen Hawkins speak... in fact, I saw him speak at BU with Steve Grossberg in the audience. He amused the audience by showing a demo that was completely indistinguishable from an ART1 implementation that takes about half an hour to program, and most of the people present had done themselves.

        He then failed to answer any substantive questions (including Steve asking him how his model differed from ART), referring us all to online videos of his lectures. I personally asked about how he could reconcile this article [oxfordjournals.org] with his predictions.. which assume a cortical hierarchy based on 'distance' (in synapses) from primary sensory cortices, rather than examining the relative lamination of various cortices. I notice since then the wikipedia article "On Intelligence" has had its 'experimental prediction' claims toned down quite a bit.

        As it happens in terms of books though, Grossberg has written several and has a ton of peer reviewed articles on this very subject. Hawkins to my knowledge doesn't have a single peer-reviewed article on HTM or anything related.

        • Re: (Score:2, Interesting)

          by FluxIntegrator ( 1094517 )
          I've studied both ART algorithms and HTMs and I cannot see how you can make a comparison, they are two completely different algorithms. A simple ART relies on *resonance* (hence it is called Adaptive *Resonance* Theory) between two only to classify the input. There is no resonance in HTMs, they are only feed forward classifiers. Furthermore, HTMs are hierarchical, the general ART algorithm is not hierarchical. In addition, HTMs train on sequences over time, the general ART algorithm trains on a set of s

      • research vs. Jeff Hawkins (Score:2, Informative)

        by Anonymous Coward
        "He who appeals to authority when there is a difference of opinion works with his memory rather than his reason."

        Please consider this post [slashdot.org] about Jeff Hawkins' history of navel-gazing idiocy in the field of neural networks.

        You worship engineers? Why this one in any case? Even if he is a good engineer, that doesn't make him a good scientist (incidentally, he's not). Maybe you're not an expert in neural networks and are deferring to someone who is, at least plausibly, an expert. But you just illustrated that y
        • Nice screed.

          Um... I notice that neither of you have actually posted any analysis or criticism of his work.

          Would either of you, by any chance, like to say something about his theories?

          Oh, and BTW: that wikipedia article you linked to appears at first reading to be nothing like Jeff's proposal.

          In the face of all this Ad Hominem, skepticism is in fact reasonable.

    • My question is why they would commit to a single algorithm in the first place? Most of the work for a system like this is in the data gathering, manipulation, and (perhaps most of all) user interface. The recognition algorithm itself will probably constitute 0.001% of the code. It's hard to believe they wouldn't make it modular and experiment with some different algorithms.

      • Re: (Score:2)

        by wanax ( 46819 )
        The idea of algorithms like this, which are supervised learning systems, is that you train them to recognize 'hidden statistics.' These tend to be things that people have little trouble recognizing (eg. faces), but that we haven't been able to describe analytically for computers. So, you're certainly right that the main job of the programmer is to choose an effective algorithm, and then train it on the available data. It turns out, though, that there are an essentially unlimited number of unique and distinc

        • Re: (Score:1)

          by Roxton ( 73137 )

          This generally can't be done to any optimum criteria until the system designer gains familiarity with the systems and dataset... so it winds up being a subjective judgment of the designer rather than a rigorous examination of the possibilities... or else this process winds up being recursive ;)

          Heh, that one left me chuckling on the way to work. Thanks, N.

    • Re: (Score:2)

      by FleaPlus ( 6935 )
      While loaded with buzzwords, this really involves nothing that's really new.

      Yeah, I haven't looked at it too intensively myself yet, but the impression I get is that most/all what Hawkins proposed has been proposed in the past. He basically took what was done in the past and made it much more accessible, which is great and all, but he really should've cited more of the prior work by others (or been more aware of it). Besides Grossberg, I think there's also quite a bit of similarity with the work of Rao [nature.com]
      • You are totally correct on the literature.. I was posting quickly ;) Rao & Ballard in particular I think influence Hawkins works (not to mention that Rao was one of the people who convinced me to go into neuroscience.. but I digress). The problem with Lee & Mumford is that it's now been known for quite a while that V1 receptive fields are not static, but dynamic in really cool ways.. Check out Ohzawa's videos [osaka-u.ac.jp] for example.
    • Other programs are as good as Jeff's at recognizing things? Show me a program that can be trained on an arbitrary set of images, and then make accurate recognitions from data which has been degraded in various ways. Basically, a CAPTCHA reader which doesn't know beforehand what the letters in the alphabet look like.

      Jeff has proposed a theory of how the cerebral cortex works, which is not in itself unusual. There's lots of people who have proposed outlandish solutions to the various problems posed by AI. T

    • Re: (Score:1)

      by sh3l1 ( 981741 )

      While loaded with buzzwords, this really involves nothing that's really new. The HTM is just a rehash of Adaptive Resonance Theory And applications like this aren't exactly new (this link downloads a .ps.gz file).
      I found the article very proactive, and dynamic. What about you guys?

    • Well, Steve Grossberg has always believed that every discovery in neural networks and AI is isomorphic to Adaptive Resonance Theory. That's why he never needs to cite anyone except himself!

      It's true that ART was an early unsupervised learning model, and it's true that some of its innovations were rediscovered later by others. But by now there's a lot going on in the field that has no real connection with ART.

      I'm not a fan of Numenta, BTW -- I think Hawkins should get back to doing what he does well a

  • Good bye privacy... (Score:3, Interesting)

    by blahplusplus ( 757119 ) on Thursday October 11, 2007 @11:53PM (#20949791)
    Yep, I knew it. These guys want to know everything, I can just imagine what kind of black-deals they can cut with major corporations for competitive advantage, using the data being fed by these satellites to determine patterns in human behaviour and using that for strategic investment. And that is only the tip of the iceberg...

    Tinfoil hat you say? One only has to look at history, Alexander thought himself a god (or wanted to be one) and man is obsessed with improving his power to dominate and control both peaceful and hostile populaces, the truth of the matter is, why let the future happen to you when you can start to predict it, and thereby shape it?

    That is what the power mongers of this world want, is some modicum of ability to guide and shape history in their favor. And if you were at the top, among competitors that may beat you to it... you'd want it too.

  • URGENT (Score:4, Informative)

    by QuantumG ( 50515 ) <qg@biodome.org> on Friday October 12, 2007 @12:09AM (#20949853) Homepage Journal
    Urban Reasoning and Geospatial Exploitation Technology (URGENT) [darpa.mil]

    The Urban Reasoning and Geospatial Exploitation Technology (URGENT) program is will develop a 3D urban object recognition and exploitation system that enables advanced mission planning and situation analysis capabilities for the warfighter operating in urban environments.

    The recognition of targets in urban environments poses unique operational challenges for the warfighter. Historically, target recognition has focused on conventional military objects, with particular emphasis on military vehicles such as tanks and armored personnel carriers. In many cases, these threats exhibit unique signatures and are relatively geographically isolated from densely populated areas. The same cannot be said of today's asymmetric threats, which are embedded in urban areas, thereby forcing U.S. Forces to engage enemy combatants in cities with large civilian populations. Under these conditions, even the most common urban objects can have tactical significance: trash cans can contain improvised explosive devices, doors can conceal snipers, jersey barriers can block troop ingress, roof tops can become landing zones, and so on. Today's urban missions involve analyzing a multitude of urban objects in the area of regard. As military operations in urban regions have grown, the need to identify urban objects has become an important requirement for the military. Understanding the locations, shapes, and classifications of objects is needed for a broad range of pressing urban mission planning analytical queries (e.g., finding all roof top landing zones on three story buildings clear of vertical obstructions and verifying ingress routes with maximum cover for ground troops). In addition, it will enable automated time-sensitive situation analysis (e.g., alerting for vehicles found on a road shoulder after dark and estimating damage to a building exterior after an explosion) that will make a significant positive impact on urban operations.

    Phase 1 of the URGENT program is developing techniques for the rapid exploitation of EO and LIDAR sensor data at the city scale to recognize urban objects down to the soldier scale. URGENT is applying image processing technology to geospatially registered 2D/3D data collected from airborne and terrestrial sources, yielding precise annotations for the objects in an urban area.

    Phase 2 of the URGENT program will develop a 3D reasoning engine to query over object shapes, locations, and classifications for rapid urban mission planning, mission rehearsal, and situation analysis. Phase 3 will focus on the integration and transition of the URGENT system to the National Geospatial-Intelligence Agency (NGA).

  • LIDAR rocks (Score:2, Interesting)

    by d474 ( 695126 )
    Feature extraction, such as buildings and trees is already being done. In fact, the dot clouds produced by LIDAR provide enough information about trees that some research is focusing on ways to automate the identification of species of individual trees, and replicating that across an entire forest. But I digress... I, for one, welcome our Numenta powered, LIDAR scanning, ORBIT-Lords.

    • Re: (Score:2)

      by Equuleus42 ( 723 )

      I, for one, welcome our Numenta powered, LIDAR scanning, ORBIT-Lords.
      LIDAR is pretty much my favorite. It's like laser light and radar mixed... bred for its skills in magic.

  • Brian Inspired? (Score:3, Insightful)

    by supersnail ( 106701 ) on Friday October 12, 2007 @01:58AM (#20950251)
    .... these being the brains that get abducted by aliens, and see images of the virgin mary in slices of toast?

    Good luck guys.
  • welcome our new ORBIT see-it-all overlords.
  • just a few hours after I wiped out Numenta's software from my HDD
  • Anyone else think for a moment that Shrub got his own Slashdot topic or just us Doonesbury fans?
  • > modeled on the technology growing inside human heads

    Last I checked, there wasn't any technology growing inside my head. Am I living in the wrong 2007 or something?

  • What exactly is the point of all this?

    Although the concept of using LIDAR to create an extremely detailed topographical map is certainly a neat (and useful) thing to do -- military and non-military applications alike, I question exactly how the AI engine is going to come into play.

    This sort of system would make sense if you were scanning for subs and stealth aircraft from space -- the sort of thing that has a regular shape. But as to our current military situation, how the heck are you going to correctly d
  • way to go darpa!

Slashdot Top Deals

Algebraic symbols are used when you do not know what you are talking about. -- Philippe Schnoebelen

Close