Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Neural Networks That Describe Images

cs.stanford.edu

Post reply on HN
Print view View original

51–60 of 63 posts

Re: Neural Networks That Describe Images

#51

Post by dTal »

jameshart wrote: post #24
arjie wrote: post #5

Fascinating. Also interesting to see the failure modes. Any human would quickly realize that the "boy doing backflip on wakeboard" is actually playing on a trampoline. Or the "two young girls playing with legos toy". Great stuff!

Right - impressive though this is, also the cat isn't black, the woman with the bananas might well not be a woman, the girl isn't swinging on a swing, the construction worker is probably not in the road, and the guitarist is tuning the guitar, not playing it. It's pretty much wrong -in detail- on every count. The weird thing is how at a glance, it seems pretty much correct. And how some people here are willing to loo…

And those are clearly plantains, not bananas!

Re: Neural Networks That Describe Images

#52

Post by gaurav_v »

Zeebrommer wrote: post #37

I'm a bit skeptic. They have several very good examples, and those are really impressive. Everything about how often these striking results occur is 'coming soon' though. And since it is neural network-based, being lucky sometimes doesn't say anything about the statistical performance. What percentage of the test dataset was labelled correctly?

Model performance is discussed in their full paper, here:

http://cs.stanford.edu/people/karpathy/deepimagesent/devisag...

Re: Neural Networks That Describe Images

#53

Post by Houshalter »

31reasons wrote: post #32

Something doesn't seem right. If we are this good in image recognition, how come we are still using captchas? Are we so good in image recognition that it can identify young girl, bunch of bananas, guitar etc just by training it from an image set of just few thousand image. Whats the catch ? On one hand google says their self-driving car can't understand all the situations on the road while this algorithm can identify…

As I understand it, reCAPTCHA now relies heavily on metadata to determine if someone is a bot. Probably stuff like their IP address, browser information, geographic location, internet speed. Then it predicts how likely they are to be a spam bot and sends them a much harder CAPTCHA if so. And they change the interface to throw off bots.

The average person who just wants to automate filling out your website form is still blocked, so it's not useless.

There is some recent research that suggests you can make images which are very hard for neural networks to identify, but still easy for humans.

Here is an example: http://i.imgur.com/K6AQRkV.png The digits on the right are just slightly changed to be harder for NNs to recognize.

For comparison, this is the amount of random noise needed to have the same effect as their method: http://i.imgur.com/Asnf2L8.png

Re: Neural Networks That Describe Images

#54

Post by aurelius »

Neural networks are impressive only in that they are able to give any kind of meaningful results at all. In the end, they are only a poor mimicry of real machine intelligence, and not much better, conceptually, than plain old nonlinear regression.

Nobody has been able to determine what the structure of a neural network should look like for any given problem (network type, number of nodes, layers, activation functions), how many iterations of the parameter optimization algorithm are needed to achieve "optimal" results, and how "learning" is actually stored in the network.

Statistical learning methods are obviously still useful, but I think the field is still wide open for something to emerge that is closer to true machine intelligence.

Re: Neural Networks That Describe Images

#56

Post by bcbrown »

aurelius wrote: post #54

Neural networks are impressive only in that they are able to give any kind of meaningful results at all. In the end, they are only a poor mimicry of real machine intelligence, and not much better, conceptually, than plain old nonlinear regression. Nobody has been able to determine what the structure of a neural network should look like for any given problem (network type, number of nodes, layers, activation functions…

What do you define 'machine intelligence' as?

Re: Neural Networks That Describe Images

#57

Post by smokeyj »

bprater wrote: post #17
kolbe wrote: post #16

Presentations like these make me realize how close we are to developing law enforcement (/police state) technology that will be very effective. I figure when the kinks are smoothed out, that we could run this on a video feed, and have crimes prevented right as they're about to happen. It's almost scary. Imagine 20 years from now, some guy pulls a gun on you, and a video feeds identifies his action, and immediately sh…

Effective and also scary. That same video feed could be archiving (for eternity) every single citizen's movement, action, or even words: "Citizen #5135: In 2015, spit on sidewalks 28x this year, jaywalked 49x, etc..."

http://en.wikipedia.org/wiki/Recorded_Future

Don't worry. Google and the CIA have your back.

/duck and covers from incoming thought police

Re: Neural Networks That Describe Images

#58

Post by xanderjanz »

aurelius wrote: post #54

Neural networks are impressive only in that they are able to give any kind of meaningful results at all. In the end, they are only a poor mimicry of real machine intelligence, and not much better, conceptually, than plain old nonlinear regression. Nobody has been able to determine what the structure of a neural network should look like for any given problem (network type, number of nodes, layers, activation functions…

Please, try implementing non-linear regression to understand images. Tell me how it goes.

Also, 'nonbody know hows learning is stored'? You very clearly have never worked with neural nets before. Experience is stored in the form of weight values.

Re: Neural Networks That Describe Images

#59

Post by xanderjanz »

ed wrote: post #22

This isn't really a breakthrough in object identification, as much as it is a clever pairing of identification with (mostly existing) language systems, is that right? Wondering whether there's any merit to sibling comments speculating this is the future of e.g. surveillance

well, this is doing more than just object recognition+language labeling. Notice how it understands the the girl is 'in' the white dress. That is a lot more comlicated that identifying a white dress and a girl.

Re: Neural Networks That Describe Images

#60

Post by jameshart »

negamax wrote: post #29
jameshart wrote: post #24

Earlier quoted context omitted.

Right - impressive though this is, also the cat isn't black, the woman with the bananas might well not be a woman, the girl isn't swinging on a swing, the construction worker is probably not in the road, and the guitarist is tuning the guitar, not playing it. It's pretty much wrong -in detail- on every count. The weird thing is how at a glance, it seems pretty much correct. And how some people here are willing to loo…

Wow.. talk about high expectations. This is really well done. Identifying multiple concepts in an image and describe it to a good degree of accuracy. And this will get better further.

No no! Don't misunderstand me! I agree: It's phenomenally impressive! It's also still completely useless at this level of accuracy.

At this point, this software is as useful at describing photographs as a disinterested teenager who is busy trying to text. "This is a picture of my mom with some dude playing I dunno like tennis or something. Whatever."

Which is really impressive! Seriously!

But closing the gap to accuracy is really important, and it's a hard hard problem.

Post reply on HN