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

Is AI Riding a One-Trick Pony?

technologyreview.com

Post reply on HN
Print view View original

201–210 of 219 posts

Re: Is AI Riding a One-Trick Pony?

#201

Post by Eridrus »

Retric wrote: post #178
bitL wrote: post #103

Earlier quoted context omitted.

The whole point of Deep Learning is that we don't want to describe math behind object recognition; it was the failed "classical" approach where people spent decades figuring out complex features which worked horribly. Deep Learning is actually pretty simple, well understood and parallelizable, and it's basically a billion-dimensional non-linear optimization. As optimization is infested with NP-hard problems, it's as…

Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant. Feature extraction also works much better when you toss a lot of data and processing power behind it. So, a lot of progress is simply more data and computing power vs better approaches. Consider how poorly deep leaning works when using a single 286.

There is work on rotation invariant CNNs, but I'm not sure why you would expect that property to just fall out of standard CNNs.

As much as architecture research gets denigrated these days, MLPs aren't what set off the revolution.

Re: Is AI Riding a One-Trick Pony?

#202

Post by neospice »

graycat wrote: post #189
graycat wrote: post #136

Earlier quoted context omitted.

It's easy to recognize a cat 95% of the time. I can write a program in 30 seconds that will recognize a cat 95% of the time. No, wait, this just in! My program will recognize a cat 100% of the time! The program has just one line: Print "It's a cat!"

Tutorial: So, with that program, whenever the picture is a cat, the program DOES recognize it. So the program DOES recognize a cat 100% of the time. The OP only claimed 95% of the time. Uh, we need TWO (2), that's TWO numbers: conditional probability of recognizing a cat when there is one (detection rate) conditional probability of claiming there is a cat when there isn't one. The second is the false alarm rate or th…

Thanks for explaining, this comment is much more useful than your original to someone not well versed in statistics like me.

Re: Is AI Riding a One-Trick Pony?

#203

Post by Animats »

nopinsight wrote: post #175
Animats wrote: post #155

I'd argue that the next problem to attack is manipulation in unstructured environments. Robots suck at that. There's been amazingly little progress in the last 40 years. DARPA had a manipulation project and the DARPA humanoid challenge a few years ago, and they got as far as key-in-lock and throwing a switch. Amazon is still trying to get general bin-picking to work. Nobody has fully automatic sewing that works well,…

I agree with your general characterization of the area. For sewing though, Sewbots appears production-ready and does not require starching the fabric. What do you think of it? http://softwearautomation.com/products/

20% real, 80% hype. There's lots of partial automation in apparel, but handling fabric is still very tough. Especially for operations after the first one, where you have to deal with a non-flat unit of several pieces sewn together. They apparently can make T-shirts, but not jeans.

They're not doing manipulation in an unstructured environment. They're trying to structure apparel sewing rigidly enough that they need a bare minimum of adaptation to variations. That's how production lines work.

Re: Is AI Riding a One-Trick Pony?

#204

Post by mikeash »

QAPereo wrote: post #195
mikeash wrote: post #55

Earlier quoted context omitted.

The other day I was walking out of my closet, turned, and nearly jumped out of my skin because some clothes hanging from the door briefly looked like a large man standing right next to me. I'm not sure that our failings only happen under unusual circumstances, but rather maybe we're just used to them and don't think about it much.

That's no failing, that's working as intended. It's far more beneficial for us (and more importantly, our successful ancestors) to be extremely wary of potential threats at the level of near-reflex. It's also important not to waste a bunch of energy running from phantoms. So you did something no computer today could; you had an instinctive reaction, which was then moderated by increasingly higher levels of reasoning.…

Just because it evolved to a point that balances the tradeoffs doesn’t make it somehow not a failure. Humans can be fooled into seeing things completely different from what’s there, just like ANNs.

Re: Is AI Riding a One-Trick Pony?

#205

Post by cc439 »

soVeryTired wrote: post #186
Retric wrote: post #178

Earlier quoted context omitted.

Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant. Feature extraction also works much better when you toss a lot of data and processing power behind it. So, a lot of progress is simply more data and computing power vs better approaches. Consider how poorly deep leaning works when using a single 286.

> Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant. But that's true of people too. How quickly can you read upside-down? If you trained on a mixture of upside-down and right way up images, and tested on upside-down images, performance wouldn't take that much of a hit.

While I can't easily read upside down text, I can instantly recognize it as not only text, but that it needs to flipped upside down in order to be read. That's something current "deep learning" AIs can't do reliably, if at all.

If I had to describe the root cause of this problem it would be that humans process "problems" rather than "things" and we "learn" by building an ever growing mental library of problem solving algorithms. As we continue to "learn", we refine our problem solving algorithms to be more general than specific. Compare that to a deep learning AI that learns by building an ever greater data library of things while refining algorithms to suit ever more specific use cases.

Re: Is AI Riding a One-Trick Pony?

#206

Post by TaylorAlexander »

cc439 wrote: post #205
soVeryTired wrote: post #186

Earlier quoted context omitted.

> Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant. But that's true of people too. How quickly can you read upside-down? If you trained on a mixture of upside-down and right way up images, and tested on upside-down images, performance wouldn't take that much of a hit.

While I can't easily read upside down text, I can instantly recognize it as not only text, but that it needs to flipped upside down in order to be read. That's something current "deep learning" AIs can't do reliably, if at all. If I had to describe the root cause of this problem it would be that humans process "problems" rather than "things" and we "learn" by building an ever growing mental library of problem solving…

I think you're describing a level of generalization above the application at hand. We could easily train a neural network to recognize the orientation of a font, and then build an orientation invariant "reading" app by first recognizing the rotation of the text, transforming it so it is right side up, and then recognizing as normal.

I tend to imagine our brains works similarly. It's not that you have a single "network" in your brain that recognizes test from all angle, but your brain is a "general purpose" machine with many networks that work together. I think current deep learning techniques are great for discrete tasks, and the improvement needed is to have many networks that work together properly with some form of intuition as to what should be done with the information at hand.

Re: Is AI Riding a One-Trick Pony?

#207

Post by graycat »

neospice wrote: post #202
graycat wrote: post #189

Earlier quoted context omitted.

Tutorial: So, with that program, whenever the picture is a cat, the program DOES recognize it. So the program DOES recognize a cat 100% of the time. The OP only claimed 95% of the time. Uh, we need TWO (2), that's TWO numbers: conditional probability of recognizing a cat when there is one (detection rate) conditional probability of claiming there is a cat when there isn't one. The second is the false alarm rate or th…

Thanks for explaining, this comment is much more useful than your original to someone not well versed in statistics like me.

Some people much prefer short comments, or so they say!

Re: Is AI Riding a One-Trick Pony?

#208

Post by markan »

zwischenzug wrote: post #200
gadjo95 wrote: post #50

The most relevant part of the article: David Duvenaud, an assistant professor in the same department as Hinton at the University of Toronto, says deep learning has been somewhat like engineering before physics. “Someone writes a paper and says, ‘I made this bridge and it stood up!’ Another guy has a paper: ‘I made this bridge and it fell down—but then I added pillars, and then it stayed up.’ Then pillars are a hot ne…

I feel like Hofstadter was one of those people thinking really deeply about AI. Anyone who doesn't know what I'm talking about should read 'Goedel, Escher, Bach', or 'Fluid Analogies'. I haven't read them in a long while, but I'm sure they're going to be relevant for decades, because they deal with the fundamental challenge of what it means to think. Backpropagation may be part of the puzzle, but the brain (and intel…

I second this recommendation! Here's some more reading for anyone interested in Hofstadter:

http://www.popularmechanics.com/science/a3278/why-watson-and...

http://www.basicai.org/blog/hofstadter-2017-09-25.html

Re: Is AI Riding a One-Trick Pony?

#209

Post by fasquoika »

kevin_thibedeau wrote: post #58
moxious wrote: post #46

Earlier quoted context omitted.

The unrestricted Turing test has been around since the 1950s as a test that hasn't changed. No one is moving the goalposts, I think it's rather the opposite. Every ten years computers learn a new trick or two and people rush to claim that this time, it's intelligent.

The Turing test is all a smoke and mirrors game. Q&A interactions say nothing about underlying self-directed initiative. Acting intelligent doesn't make it so just as a thespian doesn't become a real Hamlet by playing the role.

>Acting intelligent doesn't make it so just as a thespian doesn't become a real Hamlet by playing the role.

I think the idea is that a machine that can emulate a human is necessarily intelligent because it can emulate intelligence. It's supposed to be similar to the way that you can know that a machine is Turing-equivalent because it can emulate a machine which is Turing-equivalent

Re: Is AI Riding a One-Trick Pony?

#210

Post by fasquoika »

sgt101 wrote: post #170
hyperbovine wrote: post #163

Earlier quoted context omitted.

In fact linear regression could be used to do all of those things, most of them poorly but some of them pretty well (see dictionary learning). If you believe otherwise then you fundamentally misunderstand how neural networks work.

Ohhh - so the multilayer perceptron xor thing is all wrong? I can use bricks to build a boat, if you think I can't then you don't understand floating.

>I can use bricks to build a boat, if you think I can't then you don't understand floating.

Is this supposed to be sarcastic? Because it's absolutely true...

Post reply on HN