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

Lee Sedol Beats AlphaGo in Game 4

gogameguru.com

Post reply on HN
Print view View original

411–420 of 471 posts

Re: Lee Sedol Beats AlphaGo in Game 4

#411

Post by aprescott »

hatsunearu wrote: post #242
alanfalcon wrote: post #116

Earlier quoted context omitted.

Given that Lee was black in games one (due to luck of the draw) and three I expected he would be in game five as well. Perhaps the system permits loser to choose?

normally the color of the 5th game is chosen by the result of the 4th game, but Lee asked to change that rule and make him black, so he can have a shot at beating AlphaGo as black.

Is there a source of the rules for colour choice? I had thought it would be another nigiri as in 1st game. Choosing it based on the 4th game's result would imply Lee Sedol would have been given white. Since he won with white, isn't it an unfair advantage in general? For instance, if it were 2-2 after the 4th game.

Re: Lee Sedol Beats AlphaGo in Game 4

#412

Post by argonaut »

ktRolster wrote: post #282
argonaut wrote: post #92

Earlier quoted context omitted.

Sorry, I'm being a little academic. Overfitting is when the model fits to noise or error. Overfitting is not synonymous with "inability to generalize beyond the train and test distribution." For all we know AlphaGo has perfectly fit amateur games, but professional games are on a whole different level

Unlikely. Some of AlphaGo's moves were lousy moves, even for an amateur.

You are implying overfitting is the only reason a model ever performs poorly. That is not true. Just because a model does poorly does not mean overfitting must be the issue.

Re: Lee Sedol Beats AlphaGo in Game 4

#413

Post by dllu »

fizixer wrote: post #65
minimaxir wrote: post #4

There were a few jokes made during the round about how AlphaGo resigns. Turns out it's just a popup window! http://i.imgur.com/WKWMHLv.png

For anyone wondering, that's Ubuntu Linux (version most likely 14.04; Unity interface). off-topic: DeepMind should switch to a tiling window manager like i3 for increased keyboard-only productivity :)

The developers probably use whatever window manager they want. I'm personally a fan of i3 also.

But there is nothing wrong with keeping the frontend machine used in this Go match in default Ubuntu desktop environment since its only purpose is to play Go with a graphical user interface anyway.

Re: Lee Sedol Beats AlphaGo in Game 4

#414

Post by argonaut »

tel wrote: post #227
argonaut wrote: post #92

Earlier quoted context omitted.

Sorry, I'm being a little academic. Overfitting is when the model fits to noise or error. Overfitting is not synonymous with "inability to generalize beyond the train and test distribution." For all we know AlphaGo has perfectly fit amateur games, but professional games are on a whole different level

All depends on how you define your data sets I suppose. IGS games include some professional games which, if it is the case that AG is perfectly trained on the amateur mode, were smoothed away.

Again, the only way to tell if overfitting specifically (and not other factors that are more likely) is the issue is performance on a held out test set.

Re: Lee Sedol Beats AlphaGo in Game 4

#415

Post by meric »

greeneggs wrote: post #243
kronion wrote: post #48

After AlphaGo won the first three games, I wondered not if the computer had reached and surpassed human mastery, but instead how many orders of magnitude better it was. Given today's result, it may be only one order, or even less. Perhaps the best human players are relatively close to the maximum skill level for go, and that the pros of the future will not be categorically better than Lee Sedol is today.

Yudkowski argues that on the scale of intelligence, Einstein and a village idiot are basically right next to each other [1]. So once artificial intelligence gets close to matching the village idiot, it is not far from completely thrashing Einstein. Now if that same picture held for Go, then a situation like this would seem to be impossible. Either the computer should be much worse than a human player, or much better.…

>> It would be an incredible coincidence that, at the end of six months of training, the computer happened to be of comparable skill to humans.

I don't think it's that incredible - By 18 years old a significant proportion of high school students know more about chemistry than the best scientists up to 1800 did, combined.

There's a lot of human games for AlphaGo to look at, but if it is to exceed human level of play, it'll have to figure how to do that by itself. Look at human level games, learn to play human level.

It's quick to get to the edge of human knowledge, and slower to go beyond it.

Re: Lee Sedol Beats AlphaGo in Game 4

#416

Post by tenementfunster »

danneu wrote: post #345
simondedalus wrote: post #286

Earlier quoted context omitted.

yeah, not to belabor it, but if you can do something like be a champion in go or chess, chances are you have the mental skillset to do something exponentially more lucrative.

Though being able to compel yourself to do great things seems like a completely different skill set from being able to do great things on someone else's dime or on a team. For example, my brilliant programmer friend that can't hold a job. Or the artist that can only paint their own inspirations. Or the savant that doesn't get along with anybody.

He's probably a huge asshole?

Re: Lee Sedol Beats AlphaGo in Game 4

#417

Post by cjbprime »

sltkr wrote: post #260
avar wrote: post #259

Earlier quoted context omitted.

They've said it doesn't require that, AlphaGo running on a single machine beats the cluster they're using 25% of the time.

So based on current data, Lee Sedol is exactly as good AlphaGo running on a single machine.

There's a bit of a slight of hand in this statistic -- yes, they can do runtime on a single machine, but it took the compute power of a small country to train the neural nets that are loaded onto that one machine.

Re: Lee Sedol Beats AlphaGo in Game 4

#418

Post by taneq »

cjbprime wrote: post #417
sltkr wrote: post #260

Earlier quoted context omitted.

So based on current data, Lee Sedol is exactly as good AlphaGo running on a single machine.

There's a bit of a slight of hand in this statistic -- yes, they can do runtime on a single machine, but it took the compute power of a small country to train the neural nets that are loaded onto that one machine.

That's not really sleight of hand. Lots of things take more energy to produce than to run. It's like saying a 400W electric motor can put out as much power as a fairly fit human, but it's 'sleight of hand' because it took a whole factory to make the motor.

Re: Lee Sedol Beats AlphaGo in Game 4

#419

Post by ScottBurson »

SilasX wrote: post #395
ScottBurson wrote: post #334

Earlier quoted context omitted.

"People" don't do it; HN does it. Indented lines in a post are always monospaced, on the assumption, I suppose, that they're likely to be code examples. There's no way to turn this off AFAIK. And no, HN does not use Markdown.

I know the formatting system. My question is why the users are formatting their text (e.g. with 4 places leading each line) *suc that HN renders it as monospace, which then forces a sideways scroll on mobile and small screens. That seems to make it harder to read for some with no corresponding upside.

Oh. Well, I think they just don't realize that HN will monospace it.

I agree with you, it's annoying.

Re: Lee Sedol Beats AlphaGo in Game 4

#420

Post by ScottBurson »

DanBC wrote: post #364
ScottBurson wrote: post #335

Earlier quoted context omitted.

'>' doesn't "work"; it doesn't do anything on HN. It's just a convention that readers recognize as indicating quotation. HN does not use Markdown.

At least ">" doesn't break anything. Pre is broken on mobile, forcing users to scroll a horizontal line which is incredibly annoying if it's a long line. Here's a screen shot: http://imgur.com/Ru56wMK And pre with very long unbroken lines is even worse.

I wasn't expressing a value judgment, just trying to explain how HN works.

I agree with you that it's annoying when people post long indented lines.

Post reply on HN