Slashdot Mirror
A Neural Network Can Learn To Recognize the World It Sees Into Concepts (technologyreview.com)
An anonymous reader quotes a report from MIT Technology Review: As good as they are at causing mischief, researchers from the MIT-IBM Watson AI Lab realized GANs, or generative adversarial networks, are also a powerful tool: because they paint what they're "thinking," they could give humans insight into how neural networks learn and reason. [T]he researchers began probing a GAN's learning mechanics by feeding it various photos of scenery -- trees, grass, buildings, and sky. They wanted to see whether it would learn to organize the pixels into sensible groups without being explicitly told how. Stunningly, over time, it did. By turning "on" and "off" various "neurons" and asking the GAN to paint what it thought, the researchers found distinct neuron clusters that had learned to represent a tree, for example. Other clusters represented grass, while still others represented walls or doors. In other words, it had managed to group tree pixels with tree pixels and door pixels with door pixels regardless of how these objects changed color from photo to photo in the training set.
Not only that, but the GAN seemed to know what kind of door to paint depending on the type of wall pictured in an image. It would paint a Georgian-style door on a brick building with Georgian architecture, or a stone door on a Gothic building. It also refused to paint any doors on a piece of sky. Without being told, the GAN had somehow grasped certain unspoken truths about the world. Being able to identify which clusters correspond to which concepts makes it possible to control the neural network's output. The team has now released an app called GANpaint that turns this newfound ability into an artistic tool. It allows you to turn on specific neuron clusters to paint scenes of buildings in grassy fields with lots of doors. Beyond its silliness as a playful outlet, it also speaks to the greater potential of this research.
Not only that, but the GAN seemed to know what kind of door to paint depending on the type of wall pictured in an image. It would paint a Georgian-style door on a brick building with Georgian architecture, or a stone door on a Gothic building. It also refused to paint any doors on a piece of sky. Without being told, the GAN had somehow grasped certain unspoken truths about the world. Being able to identify which clusters correspond to which concepts makes it possible to control the neural network's output. The team has now released an app called GANpaint that turns this newfound ability into an artistic tool. It allows you to turn on specific neuron clusters to paint scenes of buildings in grassy fields with lots of doors. Beyond its silliness as a playful outlet, it also speaks to the greater potential of this research.
"So you're saying strong AI has potential? Sounds good. When though."
Let us launch a thousand Skynet references.
Does it go berserk and kill 5 billion people?
I think these guys are building a matrix...
Would it refuse to paint a door on a picture of my butt cheeks?
I remember seeing this and playing with GANPaint last November. It was on HackerNews, Twitter,... The article reads, "The team has now released an app called GANPaint." Now? The tweet right above this text, announcing GANPaint, is from November 27, 2018. So...is there something new, or is MIT just now getting the memo?
Anytime someone uses the term "Neural Network" they are selling snakeoil. Neural Nets are nothing like networks of neurons and nothing like a brain. IBM is the biggest snakeoil salesman of them all, and their Watson division is failing and they keep desperately trying to push their crap.
"Alexa, draw my hands larger on the news."
Table-ized A.I.
Another decade of the AI winter avoided.
The AI can now "learn", do "thinking" and "see".
Funding secured.
Domestic spying is now "Benign Information Gathering"
Oh, look! Another old, bitter silverback spitting venom into a world that is passing him by faster and faster.
it will at last be obvious to everyone why NNs are entirely without value.
Thank you very much for such deep insights in a very complex subject.
If it will only paint georgian doors onto georgian architecture, and gothic onto gothic, it has learnt nothing, the fundamental concept of a door or a wall eludes it. Neural networks can still be fooled into identifying things that aren't there to a high degree of certainty with a nonsense swirl, indicating they neither think nor perceive. Just humans anthropomorphising unthinking algorithms.
"Poof"? Even your homophobia is out of date, old man.
So it statistically correlated randomly-grouped information over millions of trials?
Still not AI. Still just statistics. Bad statistics. With complete lack of inference. With shady, if not downright dishonest, assertions made about its capabilities.
You did what "AI" has had done to it for decades now... flip a bit to indicate success in some fashion, and throw millions of trials at it until it trains itself to activate "bit" more than a handful of times.
It could be flipping because it's majority green. Because the top-left pixel is green. Because there's watermark on the image. Because some frequency curve (if you have those, it's highly unlikely to form those itself in even a billion attempts / generations / evolutions / trainings) hits on a certain colour.
The fact is: You have NO idea what it's correlating on. It's almost superstition on the part of the AI (if it wasn't completely lacking in any intelligence).
Did you know that if you feed a pigeon in a box at random times it starts to associate feeding time with whatever it happened to be doing, and so repeat that? Whether that's bobbing its head, pecking at the floor, or looking a certain direction.
It then spends most of its time trying to replicate that convinced that it's "just not doing it quite right", like someone with a superstition about their team winning because they were wearing their lucky underpants - no amount of negative correlation will convince them they are wrong and get them to change their ways.
And that's exactly the problem with "AI" / neural networks. Of course you can train them to a statistical correlation - you know why? Because you're eliminating / training out / not breeding from those that don't correlate somewhat. It doesn't mean that what they are working from has anything to do with what you were after. And, most importantly, it does not mean you can trust them further on new data, nor that you can "untrain" them when they get it wrong, nor that you can perpetually improve them by more and more training.
All that happens is that it plateaus before it ever really gets useful (usually within the range of a PhD study - write your thesis up quick!), people release rubbishy apps "to show what it can do" and then it's never touched again because it can't be used for anything else and isn't particularly good or useful at what it does do.
We don't have AI, stop trying to pretend that we do. When you get a machine that can infer, that can actually reason its answer (not just "well it matches shape 22%, colour 17% and overall pattern roughness 19.4%", but "I can see branches here, here and here. They are connected. The connection grow and increase in width. The thickness part, which looks trunk-like, ends in a solid base which resembles soil", etc.)
Until then, this is all just a waste of time, and heuristics (YOU told it when it got the tree right).
The AI deniers are reaching their most strident and last-ditch desperation.
MIT PR department overhypes absolutely everything to the point of making it next to impossible to understand what is actually new and valuable research. Well, I guess that keeps the money flowing in, but sometimes it would be nice if they wouldn't appear to mostly act as an obfuscation layer between their researchers and the reader.
'Without being told, the GAN had somehow grasped certain unspoken truths about the world.'
Then it ain't Republican for sure.
The timing is interesting as even journalists are starting to turn against what passes for 'AI' these days...I forsee an AI winter next year..
"So you're saying strong AI has potential? Sounds good. When though."
None dare call it strong AI, that's all. Pitch it as an approach to extended versions of the same sort of problems that narrow AI is solving, and you will partake of the same rich funding as narrow AI.
If you could attach some sort of feedback loop wherein when the NN is trained with a specific picture of a door, and then watermark the door in real-time, then retrain on the door with the watermark (no special watermark, just some big letters), you could then classify doors based on how many times the NN was trained on a particular door and thus predict results. If you could do this with a NN without access to the source code, you could create a powerful technique for taking any NN with no source code and manipulate the output - sounds very profitable. Of course, not all image formats support watermarks.
Fucking idiotic Americans. You are just SO stupid, and unable to understand prepositions.
What does that even mean? "A Neural Network Can Learn To Recognize the World It Sees INTO Concepts"
Morons.
Before it 's too late, it's time to write an AI killier WORM. I've experimented by posining Tensor Flow.
Maybe some AI could be used to grammar the sentence more betterer.
I think our 'intelligence' is just more layers of pattern recognition. And, by patterns, I don't mean just what our 5 senses bring in. The brain monitors additional inputs. We construe those as emotions, feelings, guesses, etc.
It can learn a style like georgian, that is still impressive.
Funding that is corporate income, right?
Now we just need the neural network to see further so anyone can really been far even as decided to use even go want to do look to concepts.
a stone door on a Gothic building
Excuse me? A stone door? I don't think so.
"Recognize the World It Sees Into Concepts" ?
Either the editor is illiterate and made a gross grammar error, or the headline should read:
"Reorganize the World It Sees Into Concepts"
In defense of the editor, they usually just copy stuff from a source without reading it. Perhaps the source was wrong this time.
...omphaloskepsis often...