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

The Difference Between AI, Machine Learning, and Deep Learning

blogs.nvidia.com

Post reply on HN
Print view View original

31–40 of 107 posts

Re: The Difference Between AI, Machine Learning, and Deep Learning

#31

Post by lottin »

thallukrish wrote: post #21

If I need to show 1 million cat images to train a neural net to see cats, I wonder how a human brain can figure out cats of any kind just by seeing one or two. Is there something fundamental we are missing in going about building these deep learning stuff ?

And how many different pictures of cats are there? If you use so many pictures to train your network, the chances are that almost every picture out there will already be in the so-called training set - not the same exact picture, but a very similar one. Then the whole "AI" is reduced to doing some fuzzy matching on a massive database of pictures.

Re: The Difference Between AI, Machine Learning, and Deep Learning

#32

Post by ragebol »

For machine learning and deep learning based assistive functions, like Google Now, Cortana and Siri, we let the companies behind them gather a lot of our personal data into "Big Data", because then you can do all the statistics.

I think a (more) true AI would not need all this data and just be a _personal_ assistant, not needing all the big data of other people too. Maybe initially, once, and then be a good personal assistant, learning to know you like a human personal assistant.

It would need some common sense, which is now lacking, mostly.

Re: The Difference Between AI, Machine Learning, and Deep Learning

#33

Post by vidarh »

maaaats wrote: post #22
dave_sullivan wrote: post #9

Earlier quoted context omitted.

> That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is). Can you give a specific example of what you mean? I ask because I see this sentiment often, but primarily from people who are very new to deep learning. You can definitely debug a neural network. You mostly want to look at metrics from t…

You cannot say: "This image was classified as a stop sign, because this part recognized the shape and this part recognized the color, and this part the text", which you could do with other approaches. When it doesn't discover that it's a stop sign, how do you debug it? Did it recognize the shape.. who knows?

> When it doesn't discover that it's a stop sign, how do you debug it? Did it recognize the shape.. who knows?

Barring other analytic tools (like looking at which parts contribute the most to the wrong result), the same way you test other things when you have a (somewhat) black box:

Form hypotheses and test them.

Maybe it didn't recognise the shape, so try adjusting the image to clean it up, and once you have one it recognises, try to reduce and alter the difference between them. Maybe it turns out the image e.g. has the stop sign slightly covered, making the shape look wrong, and there's nothing in the training set like that.

Maybe the hue or brightness is off and the training set is mostly all lit a certain way. Test it by adjusting hue and brightness of the test image and see if it gets recognised.

And so on.

There are plenty of other areas where we are similarly constrained from taking apart that which we're observing, so it's not like this isn't something scientists are dealing with all the time.

Within comp.sci. we're just spoiled in that so much of what we do can be easily instrumented, isolated and tested in ways that often lets us determine clear, specific root causes through analysis.

Re: The Difference Between AI, Machine Learning, and Deep Learning

#34

Post by denzil_correa »

oliwaw wrote: post #4

Deep learning is just a rebranding of "neural networks". When neural nets became unpopular in the 90s and early 2000s, people talked about "multilayer networks" (dropping the "neural") since it wasn't really useful to think about this approach from the neuro perspective (since it's such a cartoonish model of real neural networks anyway). Now that very deep networks have become possible, and various graphical models a…

Basically, Deep Learning is now back on the map due to two things - (1) Large amounts of data available and (2) Faster processing power viz. GPUs.

Re: The Difference Between AI, Machine Learning, and Deep Learning

#35

Post by oh_sigh »

thallukrish wrote: post #21

If I need to show 1 million cat images to train a neural net to see cats, I wonder how a human brain can figure out cats of any kind just by seeing one or two. Is there something fundamental we are missing in going about building these deep learning stuff ?

"one-shot learning aims to learn information about object categories from one, or only a few, training images": https://en.wikipedia.org/wiki/One-shot_learning

Re: The Difference Between AI, Machine Learning, and Deep Learning

#36

Post by nshm »

harlowja wrote: post #3

Has anyone figured out how to debug and/or analyze deep ANN? That's the problem I always had, you may get them into a trained state, but good luck figuring out any reason 'why' they ended up in that state (or even what that state really is).

LIME is a software to analyze any machine learning classifier https://github.com/marcotcr/lime, they have very good paper in KDD too http://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf

Re: The Difference Between AI, Machine Learning, and Deep Learning

#37

Post by bpizzi »

vidarh wrote: post #26
bomdo wrote: post #24

Earlier quoted context omitted.

Great question. Even a human brain has to train for ~4-5 months to become interested in shapes ( https://en.wikipedia.org/wiki/Infant_visual_development ). Once the human brain has been trained for these basic shapes for a while, it is able to quickly break down a new class (i.e. a cat) and recognize similar patterns in other images. This is something that is very similar to the way that training a deep NN works. Als…

> Even a human brain has to train for ~4-5 months to become interested in shapes Everyone who wonder how (on a superficial level) grown up humans are so good at learning new categories really should spend time around babies and toddlers and children for this reason... You quickly realise how much training and brain development it actually takes before we're capable of doing much.

By far the greatest part of the time I spent with my two toddlers (5 and 3) is spent repeating the same things, again and again, and trying to find shorcuts for learning (which shorcuts might just not exist, afaik).

Then one day they start to get it (like "fire burns"), but it's still not there for sure until they experiment it deeply multiple times.

The dev in me can't help but see this two little humans as big mighty neural networks who spend their full uptime constantly ingesting tremendous amount of data and being restlessly tuned back by adults and experience :)

Re: The Difference Between AI, Machine Learning, and Deep Learning

#39

Post by PeterisP »

thallukrish wrote: post #21

If I need to show 1 million cat images to train a neural net to see cats, I wonder how a human brain can figure out cats of any kind just by seeing one or two. Is there something fundamental we are missing in going about building these deep learning stuff ?

You don't really need a 1 million images of specifically cats - there are ML techniques that can look at a million meaningful pictures of different kinds to learn general visual features and then use a much smaller number of cat pictures (possibly just one) as a reference to what do you want to identify.

In that sense it's quite similar to a vision system of humans or other animals, which needs lots and lots and lots of early-age exposure to "learn how to see" (which is the hard part); and only after that it becomes possible to figure out cats of any kind just by seeing one or two.

Re: The Difference Between AI, Machine Learning, and Deep Learning

#40

Post by denzil_correa »

paulsutter wrote: post #6

I disagree. Machine learning is more general than AI and therefore should be the outer circle (unless you believe the meme "did a regression - called it AI") Deep learning is, yes, a subcase of machine learning, and AI may be a circle within machine learning and enclose deep learning. But truth be told, we will all regret the way we use the term AI now. Eventually the term AI will refer only to general intelligence (…

> Machine learning is more general than AI and therefore should be the outer circle

Machine learning is one of the but not the ONLY way to achieve AI. Artificial Intelligence is the objective, machine learning is one way to achieve it.

Post reply on HN