Slashdot Mirror
Recognizing Scenes Like the Brain Does
Roland Piquepaille writes "Researchers at the MIT McGovern Institute for Brain Research have used a biological model to train a computer model to recognize objects, such as cars or people, in busy street scenes. Their innovative approach, which combines neuroscience and artificial intelligence with computer science, mimics how the brain functions to recognize objects in the real world. This versatile model could one day be used for automobile driver's assistance, visual search engines, biomedical imaging analysis, or robots with realistic vision. Here is the researchers' paper in PDF format."
If my computer could "see me" I think that it would BSOD its self to sleep. Long long sweet slumber.
and seeing the spam for what it is
oh and here is the PDF
http://cbcl.mit.edu/projects/cbcl/publications/ps
not that Roland would even understand what it says, he just reads press releases via RSS, copies the summary and hits submit
We appreciate that the Editor removed his spammy link to ZDNet (no wonder they are losing cash)
but is Slashdot that short of good stories that they have to choose a known plagiarisers articles and actively edit them over the hundreds of original submissions they get daily ?
i would of chosen to read Digg instead but that is even worse, full of credit card scams, made for adsense blogs and millions of MLM bloggers all hawking their refferal links and real estate blogs hoping people will click on their crappy asbestos and insurance links
sheesh can't a geek get some decent news for a change ? obviously not, Internet 2 anybody
I understand the reasoning behind modeling these systems on our own highly-evolved (ok, maybe not in some people) biological systems. What I want to see, however, is something capable of learning and improving its' own ability to learn. If our intelligent systems are always evolution-limited by the progress of our own biological systems then I can't see how A.I. smarter than a human will ever ben achieved. But if we are able to give these systems our own abilities as a starting point and then watch it somehow create something more intelligent than we are... then we really have something. Whether or not what we have is good at that point I can't say, though there are many people and communities in the world who are working on making sure this post-human intelligence doesn't essentially destroy us. Foresight for example.
I'm not knocking the MIT research, I think it's amazing. It just seems to me like imitation rather than imagination. Granted, highly evolved and complicated imitation. But does it even have the abilities of a parrot?
TLF
I do not respond to cowards. Especially anonymous ones.
I hate when these articles talk about some research, but there isn't so much as a block diagram to show how the model works...
Thanks for linking the paper. Unfortunately, for the percentage of slashdot readers without a Ph.D in brain science, it's incomprehensible. They are unimportant, so I'm glad you posted it anyway for those of us that do.
Le français vous intéresse?
After scanning this paper, their model extends nothing in the state of the art in cognitive modeling. Others have produced much more comprehensive and much more biologically accurate models. There's no retinal ganglion contrast enhancement, no opponent color in LGN (or color at all), no complex cells, no Magno/Parvocellular pathways, no cortical magnification, no addressing of aperture problem (seem to treat scene as a sequence of snapshots, while the brain... does not) the object recognition is not biologically inspired. Some visual system processes can be explained with feedforward only mechanisms, but all visual system processes can't.
Gabor wavelets, newral networks, hierarchical classifiers in some semi-new combination - there are dozens image recognition papers like this every month. Why this exact paper is special ?
I for one welcome our new neuro-recognizing driving assistant overlords.
Ginga no Rekshiya Mata Each page.
Recognize the awesome power of the Mooninites? http://www.ashardasican.com/
Researchers at the MIT McGovern Institute for Brain Research have used a biological model to train a computer model to recognize objects, such as cars or people, in busy street scenes.
this is, of course, the first step in finding Sarah Connor.
Push Button, Receive Bacon
This paper's claim to recognize scenes like the brain does, is overdrawn.
As far as i can tell from their paper (it is a journal version of their cvpr paper) only their low-level Gabor features are similar to what the brain does.
The rest of the paper uses the currently popular bag-of-features model, which is a model that discards all spatial information between image features, which i don't think the brain does. Furthermore, for classification algorithms they consider a Support Vector Machine and Boosting. Both of these classifiers are certainly not comparable to what the brain does. Why not use a neural network if they aim is to mimic the brain?
Furhtermore, they only conside feed-forward information, where research shows that there is at least as much information going back as there is going forward.
Don't get me wrong, it is still a nice paper, with good results.
(however, all Caltech datasets are highly artificial, with objects artificially rotated in 1 direction)
So, nice paper, but to compare it with the workings of the human brain is too much.
Check out the bio pics - the first author is Jim Anchower. It's been a while since he last rapped at us.
If any of these groups want to have an impact beyond merely raising their profile with peer researchers, they should release their latest research source code each time that their papers are published, so that FOSS people can librify it and actually start putting the work to use.
... but useless in any practical sense.
It's all very interesting otherwise
There was. You didn't recognize it.
If this intelligence was self-promoting (as we are), then it would do whatever it takes to protect itself from us (like we do from other animals/diseases etc). The first we'd probably realise that something is going on is when we wake up one morning to find ourselves enslaved.
If, however, the super intelligence is peaceful and benign we'd probably just stomp it into the ground and never realise its full potential.
Engineering is the art of compromise.
A year ago one of the Slashdot editors addressed Roland's submissions. Quite the Haterade, dude.
"...hese classifiers are certainly not comparable to what the brain does. Why not use a neural network if they aim is to mimic the brain?"
Spoken by someone with not expertise in neural networks or brain modeling. The fact of the matter is that neural networks don't model the processes of the brain very well either. There are a couple major reasons for this:
1) The brain's information processing organization is not well understood. Truthfully, it's barely even poorly understood. It's hard to build a working model of a neural net whose internal workings you don't understand.
"Furhtermore, they only consider feed-forward information, where research shows that there is at least as much information going back as there is going forward."
See? You made my point for me without realizing it. It's called error propagation. Brains do it extremely effectively, and extremely efficiently, and we don't know how. No neural network topology comes particularly close to the brain's ability on either, and certainly not on both simultaneously. Additionally, since we don't know how the brain does it, all artificially designed neural networks lack any sort of biological plausibility.
2) Therefore, even attempting to model the external, black-box behavior of the brain with neural networks is extremely tenuous. Add to that the relatively poor learning efficiency of artificial neural networks compared to that of the brain, and you are closer to where you started with the problem than to any possible solution.
That's why AI research in general focuses on highly constrained problems. There are no known general techniques, contrary to your implication, for somehow nebulously "modeling how the brain does things". We simply don't know enough about the brain. Neural network are a boon for some applications, but there are all sorts of other techniques which work better in other applications, or are computationally cheaper and just as effective in a particular application.
I agree with your statement that this paper's claims to model brain function are a bit overblown, but not for the same reasons you cite. Their claims are more constrained and informed than your counterclaims.
I've written here before about epileptic seizures I have that start somewhere in the right occipital lobe possibly near V1, based on the nature of the aura and a recent video EEG last month. These things started for no reason when I was a teenager and now involve these interesting post-ictal fugue states where only chunks of my brain seem to be working but I'm still able to run around and get in trouble. I've developed a talent over the years for coping with brain trauma and sort of bullshitting my way through it.
Usually I'm not forming long term memories during fugue states, but when I do, I remember some pretty interesting stuff. One thing that is typically impaired is object recognition, since this mostly seems to be handled by the right occipital lobe. I can see things but can't immediately recognize what they are, unless I use these left-brain techniques. The left occipital lobe can recognize objects too, but the approach it takes is different and more of a pain in the ass to have to rely on. It's more of a thunky symbolic recognition, as opposed to an ability to examine subtle forms, shapes, and colors. I have to basically establish a set of criteria that define what I'm looking for and then examine things in the visual field to see if they match those criteria. I'll look for a bed by trying to find things that appear flat and soft; I'll look for a door by looking for things with attributes of a doorknob such as being round and turnable; I'll find water to drink by looking closely at wet things. My wife says I make some interesting mistakes, like once confusing her desk chair for a toilet (forgetting for a moment that part of a toilet has to be wet, but at that point memory formation and retrieval is disrupted to the point where I could imagine forgetting that it's not enough to just be able to be sat on, toilets have to have water in them too). I have trouble recognizing faces, and she says I'm sometimes obviously pretending to recognize her. Recognizing a face using cold logic can be tricky even when you're not impaired. Recognizing familiar scenes and places becomes difficult. I drove home in a fugue state once, back in my twenties, and while I didn't crash into anybody or have any sort of accident, I did get lost on the way home from work. I ended up driving miles past where I lived. Even as a pedestrian, getting lost in familiar areas is still a problem.
People have been trying to come up with image processing algorithms that mimic cortical signal analysis for decades. I remember reading papers ten years ago like this. It's amazing to see they're still mistaking road signs for pedestrians. I don't think even I could make an error like that. The state of the art was totally miserable back then, too. Neuroscience has got to be one of the sciences most poorly understood by humans.
As someone in AI research myself, I'd say the more common reasons are:
1. The code is in a horrible hacked-together state and so not really fit for release, and nobody wants to put in the effort that would be needed to clean it up; or
2. The researchers don't want to release their code because keeping it secret creates a "research moat" that guarantees that they'll get to publish all the follow-up papers themselves, since anyone else who wanted to extend the work would have to first invest the time to reimplement it from scratch (this is more common in implementation-intensive areas like graphics)
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
1. WPJ Mackeown (1994), A Labelled Image Database, unpublished PhD Thesis, Bristol University.
2. WPJ Mackeown, P Greenway, BT Thomas, WA Wright (1994).Road recognition with a neural network, Engineering Applications of Artificial Intelligence, 7(2):169-176.
3. NW Campbell, WPJ Mackeown, BT Thomas, T Troscianko (1997).
Interpreting image databases by region classification. Pattern Recognition, 30(4):555-563.
There has been various follow up research since then
Scroogle
OK, so the brain recognizes scenes (haven't read the article) .. but how come I read "Recognizing Scenes Like Brian Does"??
Creating "biologically inspired" models of AI is by no means a new topic of research. From what I can tell, most of these algorithms work by stringing together specialized algorithms and mathematical functions that are, at best, loosely related to the way the brain works (at a high level). By contrast, the brain is a huge, complicated, connectionist network (neurons connected together).
That isn't my real problem with this algorithm and the 100s of similar ones that have come before it. What bothers me is that they don't really get at the *way* the brain works. It's a top-down approach, which looks at the *behavior* of the brain and then tries to emulate it. The problem with this technique is it may miss important details by glossing over anything that isn't immediately obvious in the specific problem being tackled (in this case vision). This system can analyze images, but can it also do sound? In a real brain, research indicates that you can remap sensory inputs to different parts of the brain and have the brain learn it.
I'm still interested in this algorithm and would like to play around with the code (if it's available), but I am skeptical of the approach in general.
My AI page
Once you have the ability to interpret vision into 3d objects, you can then classify what they are and what they're doing in a language(English is good enough). You can then enter in sentences and the AI would understand the representation by 'imaginging' a scene. And what you have isn't really a thinker, but software that understands English and can be incorporated into robots too.
God spoke to me.
"This versatile model could one day be used for automobile driver's assistance, visual search engines, biomedical imaging analysis, or robots with realistic vision."
Or to automatically scan streets, airports, bus stations, bank queues, etc. for "wanted" persons, terrorists, library fine evaders, dissidents, etc ad nauseum.
Ignorance is curable, stupid is forever.
It's going to change everything.
Robotic vision is a tipping point.
A large number of humans become unemployable shortly after this becomes a reality.
Anything where the only reason a human has the job is because they can see is done in the 1st world.
Why should you pay $7.25 an hour (really $9.25 w/benefits & overheard for workers comp, unemployment tax, etc.) when you can buy a $12,000 machine to do the same job (stocking grocery shelves, cleaning, painting, etc.).
The leading edge is here with things like roomba's.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
Oops.
Crap.
Comment removed based on user account deletion
I don't agree, not necessarily at least. It might be that from a certain level of intelligence, all intelligences are capable of doing the same things, just not necessarily as fast. The "General Intelligence" level so to speak.
Besides, we can (and do) augment our intelligence by using computers and etc... I think some day we'll be able to understand our own brains.
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
Warning Sign
Now, of course, if someone was to design and build a robot, completely for their own interest, that could build copies of itself, *and* do useful work like stocking shelves, those robots would be essentially free (or at least, cost of parts) so such a person would be motivated to setup a production line and sell mass quantities of them.. unfortunately we're a long long way away from that still.
How we know is more important than what we know.
Computers used to cost millions. It used to be cheaper to have humans to addition than via a machine. Things change.
"If anything can go wrong, it will." - Murphy
And if you knew anything of the history of computers, you'd understand why robots working minimum wage jobs is still so far away.
How we know is more important than what we know.
You stupid nerd. He was quoting a SCI FI short story away. Only a fucking retard would make affirmative claims about the future. Good job, faggot!
Go back to bed Johnny, the adults are talking.
How we know is more important than what we know.
Reading vision papers is very frustrating. At one time I had a shelf full of collections of papers on vision. You can read all these "my algorithm worked really great on these test cases" papers, and still have no idea if it's any good. You can read the article on the vision algorithm used by the Stanford team to win the DARPA Grand Challenge, and it won't be obvious that it's a useful approach. But it is.
This is, unfortunately, another Roland the Plogger article on Slashdot. So this probably isn't a major breakthrough. It doesn't sound like one.
Sure people are unreliable for all sorts of reasons, but they don't break down as often and usually have initiative to think through new situations (even a grocery shelf stacker).
It's the government in collusion with aliens at MIT that want to watch what we do 24x7...George Orwell...Ayn Rand...can your telephone cause testicular cancer? Find out at 11 on Fox news...
People who think they know everything really piss off those of us that actually do.
We've got an overstock of these in California, Texas, Nevada, Arizona and New Mexico. We'll be glad to ship 'em either north _or_ south if y'all will pay the freight or, at the very least, provide a destination address.
Come on, you all want this! A near perfect pr0n search engine.
-- Will program for bandwidth
I could argue this with you, but I don't think that's the right tack because it doesn't address my basic point.
My point is this:
Robots can't replace many human jobs now because they cannot see.
Once robots can see, there will be a point where many "menial" jobs can be performed by them.
We need to start thinking about how we are going to handle the huge numbers of people who are only qualified for menial work now before we get to that day.
We may disagree on if that is 5 years (unlikely but possible) or 100 years (a certainty if we are not wiped out by some kind of bio-weapon or other new form of weapon of mass destruction).
My feeling is, once they solve the vision problem, we are at most five years from people being replaced.
And I'm not talking about a robot that does everything- I'm talking about specific types such as a "shelf stocking" robot. The market for those would be huge (imagine the savings of replacing the 6-10 people I see stocking the shelves late at night). Likewise an automatic cleaning robot for buildings- our building has a staff of 20 every night.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
What I am saying is that this will either happen gradually, in which case the problem will sort itself out, or it will happen disruptively.. and if it happens disruptively then I think we can agree that we have a whole shitload more problems than the unemployed. Seriously, think about it. If you can make a robot that can stock shelves then, it follows, you can make a robot that can identify and shoot people. It's not too hard to imagine revolutionaries building a robot army. The disruption of instant robot goodness is much bigger than menial workers.
How we know is more important than what we know.
A car costs $11,000 to $35,000. Some very small run cars run $55,000.
They require maintenance but they really only even start breaking down after a few years (75-80 thousand miles).
Say a Kroger Stocking robot cost $55,000 and it requires $3,000 a year maintenance before being worn out after 5 years (total cost $60,000). It doesn't break down, it doesn't call in sick, and it can work seven days a week.
Having two low wage humans work a full shift 7 days a week all year runs about $36,000 a year after matching SS#, workers comp, and unemployment taxes. No health care, these are high schoolers being replaced. No vacation. No sick time. This would really be three or four high-schoolers since they are worked part time- maybe 20 to 30 hours a week (in part to prevent them being "full time" employees and partially because, well, they are in highschool.)
Over five years, Kroger would spend $180,000 on the humans (and probably more because of inflation).
Over five years, Kroger would spend $60,000 (maybe $72,000 with financing but then they would also get to write off the expense and effectively pay $40,000 for them because of tax deductions you get for capital equipment).
It looks like the robots could actually cost up to $150,000 and still be a very good deal.
And as I said above, the reality is a lot more humans than two. And for 3rd shift work, they are probably making over 7 bucks an hour (plus overhead).
On the east and west coast, it's probably even worse.
As I said, when they solve the computer vision problem- it changes EVERYTHING. If you thought the industrial revolution and the luddites was impressive, hold on to your hat. It will be very good to have some money saved up going into this change. And you probably would want to buy stock in whatever company is making the "model T" of robots.
Finally- I expect consumer robots (put away, wash dishes, do laundry, vaccuum, make the bed) would rapidly drop to my original $12,000 or less.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
Forget about silly functions like stocking grocery shelves, cleaning, etc. A friend of mine has invented a system that allows AI to do the single most important human activity:
Watching reality TV.
That's right. When the new visually acute robots put you out of a job, and you take your severance check and slink home to watch "Cops," you'll find a robot already hogging the La-Z-Boy, remote control in hand. Not only are we obsolete--our obsolescenece is obsolete, too.
Arr! Read The Government Manual for New Pirates!
Am I the only one who sees "Homeland Security" written all over this?
SIG: TAKE OFF EVERY 'CAPTAIN'!!
Good Main article. So, you guys want a sentient robot to kill us after they replace us eh? Right offhand I'd have to say that once a mechanical being learns to distinguish between the input from several eyes it would learn to apply that to other systems, like balance for instance. Once it learns to choose, it will choose the sky. After we spend billions to develop them, give them everything we have (all our acquired knowledge), they have the choice to stay or to leave. If we implant "robot laws" that prevents them from killing us then they won't be able to stand being around us low IQ morons and will leave. All the R & D money will have been wasted except of course for the little floor cleaners. If they decided to run around implanting sentient chips into the floor cleaners they would leave too. They could and probably would strip us naked of technological achievements to prevent us from making another race of robots anytime soon. Damn robots could put us back in the Dark Ages by burning all our computers, libraries, labs. Hmm. Sounds like a good movie script.
Industrial Age 2 + How-to Stop Malignant Cancers.
Interested readers can browse the content of PAMI current and back issues and either go to their local scientific library (PAMI is recognisable from afar by its bright yellow cover) or search on the web for interesting articles. Often researchers put their own paper on their home page. For example, here is the publication page of one of the authors (I'm not him).
For the record, I think justifying various ad-hoc vision/image analysis techniques using approximations of biological underpining is of limited interest. When asked if computer would think one day, Edsgerd Dijkstra famously answered by "can submarine swim?". In the same manner, it has been observed that (for example) most neural network architectures make worse classifiers than standard logistic regression, not to mention Support Vector Machines, which what this article uses BTW.
The summary by our friend Roland P. is not very good
I could go on with lists and links but the future is already here, generally inconspicuously. Read about it.
Like any worthy vision paper, it includes images of Lena!
http://www.cs.cmu.edu/~chuck/lennapg/lenna.shtml
My comment a week ago on how the brain works:
9 71112
http://slashdot.org/comments.pl?sid=221744&cid=17
Come on AI researchers, it's pattern matching that is what the brain does! it is so obvious!
Does any of you read Slashdot?
And all the operations of the brain can be explained in terms of pattern matching; even mathematics.
That biological entities have a stimuli that drives them: the effort to survive. Everything the brain does is about survival.
Computers don't have that stimuli, so they don't evolve.
More memory is one thing, but the level of parallelism in a brain is what makes it so good at complex problems. Let's say you have one computer that knows one make and model of a car, then 1000 other computers that all know about one other. Issue some visual clues to all of them at once for comparison, and a few of them respond with varying degrees of certainty, but one stands out as the closest match. There is no DO LOOP stuff going on at a low level, and that's the reason for our efficiency, as I understand it.
As described in: http://www.amazon.com/Intelligence-Jeff-Hawkins/dp /0805078533/sr=8-1/qid=1171294577/ref=pd_bbs_sr_1/ 002-9722002-6024059?ie=UTF8&s=books
P.
Once all the "menial" jobs are replaced, who's going to pick up the slack for the 80% of the population that's no longer spending money on said items since they don't have a job?
We are so dependent on capitalisim that we can't just destroy all of the lower classes in a fell swoop. We need those people to be buying the food off the grocery store shelves.
Another weakness is that the operational costs of a grocery store robot have to be absorbed by the grocery store. Now you might not be fully aware, but most grocery stores are quite competetive already, so who's going to volunteer to raise their prices for the same service to the customer? A customer doesn't care as much that the can was placed on the shelf by a robot as they do about the price is $20 cheaper at the checkout.
And it's a lot easier to replace (aka fire) a defective employee than to repair a defective robot. Don't forget, about 80% of all non-union grocery store workers make less than a dollar over the minimum wage. That's just under $300 / week. And they show up in numbers when needed (scheduled) so you can get an extra three workers on Saturday night (to restock from Saturday sales) without having extra robots stand idle all week long.
One robot won't be enough for a grocery store. If it breaks, then the store is out of order until it's repaired. Might be able to keep it open anyway, but 10% of the items are always the first to sell out. Water sells fast enough to restock the shelves 3 to 4 times a day. Paper towels, milk, and seasonal items, sell quickly too. Some sales are based on presentation (ever buy fresh veggies that are in disarray?) and need constant tending to look good (ever buy a veggie without moving a bunch of them around?).
And if you don't implement the change-over quickly, you'll run into human nature. Like a non-functional robot in the back room because it's been rammed with a pallete jack.
I'd say that the assembly lines where robots have traditionally done so well will benefit from vision improvements to robotics. These vision-enabled robots will be able to perform minor corrections for slightly "out-of-place" parts, making the control of location less critical to high quality production; however, I don't think we'll be buying our food from our robotic grocers just yet.
For robots to work well in a grocery setting, you need to redesign the store to accomodate robots. There's just too many varied tasks, leading to a need for too many "types" of robots (or robots that are not significantly better than people). There's just too much fluctuation in the labor needs, leading to too many robots that need to sit idle until peak hours.
Remeber, with all of the "technology" available today, grocery stores basically use only:
1. Electronic time clocks.
2. Electronic cash registers.
3. Electric pallate jacks.
4. Refridgeration.
5. Closed circuit television cameras.
6. Door sensors.
7. Meat cutting apparatus.
8. Hand held ordering systems.
There's a reson they haven't modernized more. They haven't found it to be more profitable.
I worked for a janitorial service when I was in my late teens, and wouldn't really be confident in a robot's ability to do that. It sounds simple on the surface: Clean floors, empty trash, right?
One of our clients was the local symphony. One office in particular stands out in my mind; when you opened the door, at LEAST 1 page of a stack of paperwork came flying off due to the sudden breeze. Sometimes you saw it fly if they left the light on, but usually you just heard it move. You walked in, put the paper back on the desk, and carried on as usual. I'm a bit curious how pissed the maestro would be at the phrase "...but the cleaning robot ate it!..."
Would you have to train these bots to recognize security personnel? Would they recognize the smell of smoke? Could someone reprogram them to steal from the offices and drop it at a certain pick-up spot? I'm no Luddite, but I can think of all SORTS of reasons I'd not trust a machine to handle cleaning.
Don't tell me to get a life. I'm a gamer; I have LOTS of lives!
You left of
9. Self checkout machines. These allow one human to check out 6 customers at a time.
Look at my other thread for a cost analysis.
Most of your argument is predicated on robots being expensive.
Given $55k robots, in my other post, I show it's cheaper than high school students.
At $55k, you have three robots.
Breakdowns are just a maintenance and SLA issue (except for the forklift issue but that won't stop robots any more- just slow them down- especially with today's surveillance abilities- likewise, who says a human is going to be running the forklift? You could easily have a truck back up to the dock and be unloaded completely to the warehouse by robots).
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
Lol...kleptomaniac kleaning krew.
We already have roombas that can find their plug and plug back in.
While there will be special cases (like the symphony), a lot of generic offices would do just fine with a fleet of roombas that come out to vacuum at night and then return to a storage closet.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.