Moravec's paradox • Hacker News Board

Re: Moravec's paradox

#11

Post by msandford » Fri, Dec 14, 2012, 10:34 PM UTC

It's only difficult because computers are digital devices and all the "hard" things for computers/robots to do aren't done in hardware. Trying to have a single CPU do all of the things a robot needs to do is asinine.

Making a robot hand pick up an egg and a cup of coffee and turn a wrench isn't difficult provided that you build in similar feedback loops and low-level "firmware" that the brain does for us, unconsciously.

But if you did that it would take tens of kilowatts to run a halfway decent robot. And that's clearly ridiculous! So nobody does it.

Re: Moravec's paradox

#12

Post by c8ion » Fri, Dec 14, 2012, 10:40 PM UTC

This doesn't seem very paradoxical to me, and at a layman's level I think one good parallel between a human's "operation" and a computer's operation with regard to this question is as follows . . .

Even as a non-programmer (I am a programmer) I might relate well to an ordinary desktop/laptop running my Excel spreadsheets. I can create a spreadsheet, enter data in cells, enter formulae, format the content beautifully, specify and view charts of the data I'm entering and information I'm computing. I might be able to respect and appreciate the beauty and complexity of how the spreadsheet program was implemented in an abstract sense. I might describe to another person my ideas about how the spreadsheet program was created, its major features and concerns, and its obvious complexity. What I'd be missing though, likely, is (a) the complex interface between what I see and what supports that experience behind the scenes; and (b) the 50+ years of computing technology under the hood that has evolved to support my narrow and visible relations with my Excel spreadsheets.

From the user's view, the Excel spreadsheets, Windows Explorer, the Start button, etc., are the aspects of the computer analogous to a human's thought processes. They're visible and explainable. The user might have some vague notion that files are stored on disk, that there's something called a CPU, that does the computer thing, etc. The user has no clue, though, that the Excel spreadsheet program itself contains but a very small portion of the effort to make its visible manifestations happen. There's an enter support system from file system, CPU, memory, buses all over the place, GPU, video display, chips, specialized interfaces to I/O and other subsystems, ASIC's, semiconductor physics, electricity, magnetism, etc. The hardware, firmware, and software for the latter have had 50 years to evolve and mature. To a normal user these aspects aren't understandable. They understand Excel.

And so for us, we can understand and describe human thought and cognition in an abstract way. But most thought is below the level we're conscious of, and supporting that thought is an entire interface with the physical elements of the body, its nervous system and autonomous function, and the interface of these with the brain.

Re: Moravec's paradox

#13

Post by tgflynn » Fri, Dec 14, 2012, 10:48 PM UTC

Breakthrough wrote: post #10

tgflynn wrote: post #6

It's an interesting observation and certainly something one needs to be aware of in thinking about intelligent systems but I'm not convinced that the notion that perception is intrinsically harder than logic is quite true. I think the difficulty of a problem is highly dependent on the representations and models used. Computers were developed based on logical and mathematical principles so it makes sense that they are…

There's also the difficult task of real-world interaction (or as the article puts it, low-level sensorimotor skills), although I suppose this is what you mean by perceptual problems. Most things humans create are based on rules (e.g. games, markets, governments), and rules can be easily taught to computers as they're just abstract logical ideas. Even for probabilistic problems, you can certainly teach a neural networ…

Well what I mean by "hard" is that I can train a neural network to do a reasonably good job of recognizing say handwritten characters given some amount of training data.

My attempts to train similar networks to learn the rules of chess (just the rules, I'm not even talking about trying to win) have not led to good or steadily improving performance, despite the fact that there's effectively no limit to the amount of training data that can be generated for chess.

There are a number of possible reasons for this of which I think 2 likely ones are that:

1) The networks I'm using have insufficient computational/storage capacity to learn the rules of chess.

or

2) Even if (1) is not the case gradient descent is unlikely to find a sufficiently good near optimum because the response surface is too complex.

Re: Moravec's paradox

#14

Post by justhw » Fri, Dec 14, 2012, 10:49 PM UTC

Certainly true, but perception and mobility as basic as they are, are a lot complex in nature than intelligence.

Re: Moravec's paradox

#15

Post by Confusion » Fri, Dec 14, 2012, 11:09 PM UTC

What does it take to have a program come up with the theory of relativity, given the knowledge that was available in 1904?

I think there are all kinds of reasoning skills that we've never been able to test, because they depend on perception and motor skills. It seems possible those would take many more computational resources. I find it hardly surprising that feeding a program abstractions and allowing it to reason about those abstractions is simple. It's the interacting with the real world, correlating abstractions with the real world and coming up with useful new abstractions, that's hard.

I don't think we'll ever have an AI until something is built that can freely interact with the world, freely gather data and freely modify itself to enhance all its abilities. An AI without pressure sensors that ever touched sand will never understand the universe.

Re: Moravec's paradox

#16

Post by Breakthrough » Fri, Dec 14, 2012, 11:10 PM UTC

tgflynn wrote: post #13

Breakthrough wrote: post #10

Earlier quoted context omitted.

There's also the difficult task of real-world interaction (or as the article puts it, low-level sensorimotor skills), although I suppose this is what you mean by perceptual problems. Most things humans create are based on rules (e.g. games, markets, governments), and rules can be easily taught to computers as they're just abstract logical ideas. Even for probabilistic problems, you can certainly teach a neural networ…

Well what I mean by "hard" is that I can train a neural network to do a reasonably good job of recognizing say handwritten characters given some amount of training data. My attempts to train similar networks to learn the rules of chess (just the rules, I'm not even talking about trying to win) have not led to good or steadily improving performance, despite the fact that there's effectively no limit to the amount of t…

Great response, I must say.

As a conjecture, do you think splitting the logic up into several smaller neural networks with different objectives (i.e. for chess, one evaluates defensive maneuvers, one for attack, and so on) would alleviate the problem? Or at least improve the performance of the machine as a whole...

Re: Moravec's paradox

#17

Post by thyrsus » Fri, Dec 14, 2012, 11:17 PM UTC

Restatement in pictures: http://abstrusegoose.com/496

Re: Moravec's paradox

#18

Post by osetinsky » Fri, Dec 14, 2012, 11:30 PM UTC

an interesting example of this (machine listening):

http://en.wikipedia.org/wiki/Source_separation http://en.wikipedia.org/wiki/Cocktail_party_effect

Re: Moravec's paradox

#19

Post by tathastu » Fri, Dec 14, 2012, 11:31 PM UTC

This may also be an artifact that in terms of "intelligence" we have focused mostly on supervised learning as opposed to unsupervised learning; recent reversals in this trend have been shown to be surprisingly powerful [1].

Consider this: While reading, most humans use a different part of the brain to register consonants and vowels [2]. No matter how much we like to think we learn language in an orderly fashion, that is not the case. Our reading and speaking skills are simply built over time and experience by having neurons connect as we experience visual words and other people talking; formal language instruction probably plays a secondary role of attaching labels to already built neural networks.

[1] http://www.nytimes.com/2012/11/24/science/scientists-see-adv...

[2] http://www.nature.com/nature/journal/v403/n6768/full/403428a...

Re: Moravec's paradox

#20

Post by joe_the_user » Fri, Dec 14, 2012, 11:35 PM UTC

saulrh wrote: post #3

Roboticist here. This is actually a huge problem in robotics and causes all sorts of problems for real robots. For example, my current project is to teach robots how levers work.

Well,

Teach as in "program", right?

It seems like the problem is that computers and robots don't learn in same fashion as human and thus the process of "teaching" them things in their not learning concept X in same fashion as humans - ie, they don't learn generalizations such a way that are "ready at hand" to use when the appropriate situation arises.