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

What a Deep Neural Network thinks about selfies

karpathy.github.io

Post reply on HN
Print view View original

51–56 of 56 posts

Re: What a Deep Neural Network thinks about selfies

#51

Post by misiti3780 »

pramodliv1 wrote: post #12
misiti3780 wrote: post #7

One thing I always found interesting is Lecun is credited with developing covnets, but Hinton is apparently credited with scaling them and showing the world how great they are in the paper from 2012 - why was Hinton's group (Toronto) able to publish these ground breaking results before Lecun's group (NYU)

Geoff Hinton answers this question in episode 6 of the Talking Machines podcast. http://www.thetalkingmachines.com/blog/2015/3/13/how-machine... Geoff Hinton had grad students who wanted to work on the problem, but Yann LeCun didn't. "In about 2012, it should have been Yann's group, but Yann was unlucky, he didn't have a student who really wanted to do it. But we had a couple of students who wanted to do it and we to…

interesting - i took the course but did not notice that - thanks!

Re: What a Deep Neural Network thinks about selfies

#52

Post by Lawtonfogle »

JabavuAdams wrote: post #32

How to take a good selfie: don't be black or dark-skinned, unless you're a celebrity. How do we prevent our AIs from learning racism? EDIT> Informative article, BTW. A good read.

If a given question has an answer that is due to racism, the answer is still the answer. For example, if society has some underlying racism that factors into what it considers attractive, that doesn't change what it considers attractive.

I don't think these algorithms are learning racism. They are only being blunt in revealing what already exists.

Re: What a Deep Neural Network thinks about selfies

#54

Post by JabavuAdams »

Lawtonfogle wrote: post #52
JabavuAdams wrote: post #32

How to take a good selfie: don't be black or dark-skinned, unless you're a celebrity. How do we prevent our AIs from learning racism? EDIT> Informative article, BTW. A good read.

If a given question has an answer that is due to racism, the answer is still the answer. For example, if society has some underlying racism that factors into what it considers attractive, that doesn't change what it considers attractive. I don't think these algorithms are learning racism. They are only being blunt in revealing what already exists.

> If a given question has an answer that is due to racism, the answer is still the answer.

That's why it's important to be clear about the question. This ConvNet doesn't really answer the question "What makes a good selfie". It answers a much narrower and more complicated to state question.

The absence of reflection in the system means that if it's used to answer a question that's superficially similar to the designer's intent, there's no way to reason around the bias in the training data.

Imagine I'm a Canadian who trains an automated turret to classify friend / foe based on data from Afghanistan and Iraq. I've not trained the system to answer "Is this group of pixels a friend / foe", in the general sense. If the system is used outside the narrow context of its validity, say in Northern Ireland, or in a civilian Muslim neighbourhood in Paris, we should expect bad results.

So you're right to point out that the racism is in the social context. But I'm arguing that we don't actually want a classifier to learn that if there's a good chance it'll be used in a way that discards or ignores that social context. Same as using an expert system outside its domain.

Re: What a Deep Neural Network thinks about selfies

#55

Post by stefs »

netheril96 wrote: post #48
nl wrote: post #37

Earlier quoted context omitted.

This is more wrong than right. The example is correct, but not for the reasons stated. Humans are very, very good at face recognition . However, CNNs are pretty close to human performance for face detection. Only after you apply tons of handcrafted optimizations, which are mostly black art, will you get close to or surpass a human's capability. Without much domain specific tuning, an AI's insight is far from reliable…

A GoogleNet or VGGNet has tons of parameters. How many convolutional layers are stacked together, the size and stride of each one, where to put the dropout layers, where to put the full connection layers, how they are connected together, global learning rate and momentum and decay, local learning rate and momentum and decay, each of these myriad parameters have an unpredictable effect on the final result. The initial…

with the training/test data sets, wouldn't it be possible to find the best parameters with a genetic algorithm? i mean, sure, it'd take really long ... well, probably too long.
Post reply on HN