“Less than one”-shot learning

Re:“Less than one”-shot learning by dmurray on Sunday October 18, 2020 @07:34PM (#24822016)

Transfer learning is a thing though. If you train your network with thousands of pictures of cats, dogs, chickens, birds, goats but no horses, it's possible you can teach it to recognise a horse with a single additional image.

Not sure exactly how good the state of the art is compared to human children on that task, but it can't be too far off.

[ Parent | on HN ]

Re:“Less than one”-shot learning by breck on Monday October 19, 2020 @02:13AM (#24823723)

Ah, the transfer learning is the more important point, dominating my point on augmentation.

I can show a 2 year old a single picture of a horse and have them learn it, but only after training them on 5 billion pictures of non-horses.

[ Parent | on HN ]

Re:“Less than one”-shot learning by YeGoblynQueenne on Monday October 19, 2020 @08:11AM (#24825598)

But how exactly do you "train" a 2-year old on 5 billion pictuers of non-horses? And at what point does the child learn to recognise images of anything?

I mean, how do you know it takes 5 billion images of non-horses before the child can learn to recognise a horse? Even if the child sees 5 billion images of non-horses, who says that they haven't learned to recognise the non-horses and the horses from the first of those 5 billion images? After all, I don't know that children stay transfixed for hours staring at horses and non-horses while their brains process all those billions of images until they finally get it.

I think you are making an effort to explain away something that is not very well understood by modern science, by analogy with machine learning, even though there is no good reason to suppose that the two are connected in any way.

[ Parent | on HN ]

Re:“Less than one”-shot learning by breck on Monday October 19, 2020 @12:18PM (#24827804)

24 hours a day times 3600 seconds per hour times 60hz times 1000 = approximately 5 billion.

Just a ball park figure for how many “pictures” they have seen. Probably off by a few OOM, but point holds.

I think there is a very good reason to think machine learning and human learning are connected. First, I’d say it’s largely true the people who have made the most impact in the former have all studied the way the mind works (as far as science allows), and tried to emulate that in machinery. Second, experimentally the phenomena observed are increasingly similar (deep dream, for example).

[ Parent | on HN ]

Re:“Less than one”-shot learning by YeGoblynQueenne on Tuesday October 20, 2020 @05:41PM (#24842634)

I like to quote Yann LeCun on how neural nets work like our minds:

IEEE Spectrum: We read about Deep Learning in the news a lot these days. What’s your least favorite definition of the term that you see in these stories?

Yann LeCun: My least favorite description is, “It works just like the brain.” I don’t like people saying this because, while Deep Learning gets an inspiration from biology, it’s very, very far from what the brain actually does. And describing it like the brain gives a bit of the aura of magic to it, which is dangerous. It leads to hype; people claim things that are not true. AI has gone through a number of AI winters because people claimed things they couldn’t deliver.

https://spectrum.ieee.org/automaton/artificial-intelligence/...

Also, like I say above, it doesn't matter how many images a human sees- what matters is how many she needs to see before learnign to recognise a thing. The example of an unchanging, two-dimensional caricature of a horse is evidence enough that, even if we do see billions of "images" as you say (I'm not sure it makes sense to speak of "images" int the sense you use it) we don't need to see all those billions of them before we learn what things look like.

[ Parent | on HN ]