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

AlphaGo beats the world champion Lee Sedol in first of five matches

twitter.com

Post reply on HN
Print view View original

191–200 of 596 posts

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#191

Post by drawnwren »

DavidSJ wrote: post #135
Fede_V wrote: post #93

Earlier quoted context omitted.

That's incorrect. The features that AlphaGo uses are not pixel level features, but board states - and the architecture between AlphaGo and the Atari network is completely different. It's still an incredibly achievement - but it's important to be accurate.

For AlphaGo, a "pixel" is a point on the board. It uses essentially the same convolutional neural networks (CNNs) that are in state-of-the-art machine vision systems. But yes, the overall architecture is rather different from the Atari system, due to the integration of that CNN with Monte Carlo Tree Search.

Sorry, you're off base a bit. The Atari system did use a Deep Neural Network / Reinforcement algorithm, but as the original poster was trying to point out, the rules of Go were very much hard coded into AlphaGo. From what this [1] says, multiple DNNs are learning how to traverse Monte Carlo trees of Go games. The reinforcement piece comes in choosing which of the Go players is playing the best games.

While the higher portions do share some similarities with the Atari system, at a basic level this is a machine that was designed and trained to play Go. AlphaGO is 'essentially the same' as the Atari system in the same way that all Neural Networks are 'essentially the same.'

Is this an extremely impressive accomplishment? Yes. However, doesn't seem to qualify as anything close to generalizable.

[1] http://googleresearch.blogspot.com/2016/01/alphago-mastering...

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#192

Post by kqr »

exDM69 wrote: post #179
blue1 wrote: post #127

Earlier quoted context omitted.

The rules can be explained in 1 minute, but the game takes some time to just start making sense. I suggest starting on a 9x9 or 13x13 board. The regular 19x19 has too much strategic depth and noobs feel lost on it.

Many Go players suggest starting with Atari Go (aka Capture Go). It has the same rules as Go, but the starting position is predetermined and the winner is the player to capture the first stone. You only need to play a few rounds of Atari Go, say 30 minutes to an hour to get a grasp of the capturing rules and then you can move to a 9x9 or 13x13. I'd go straight for the 13x13 because it's not that much bigger but it ha…

The drawback with Capture Go is that it emphasises the capturing part perhaps a bit too much. I prefer introducing players to a variant with the same rules as capture go, except the winning condition is "having the most pieces on the board". This is essentially the same thing as regular go, but without all the fuffing about with learning scoring and such.

When played on a small enough board, the games take about as long time as capture go games.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#193

Post by onion2k »

Houshalter wrote: post #116
onion2k wrote: post #52

Earlier quoted context omitted.

Yet people will still tell that worrying about AI taking over is like worrying about overpopulation on Mars, and that this is a problem at least 50 years out. As hard as writing AI for a problem space like "how to win at Go" is, it's several orders of magnitude easier than creating a general AI with the self-awareness required to see us as a threat.

There is a lot of progress being made in AI right now. Hard problems that were expected to take decades, are being beaten regularly. Who is to say how much AI could advance in the next 20-30 years? Do you really believe there's less than a 50% chance strong AI won't be invented in your lifetime?

There is a lot of progress being made in AI right now. Hard problems that were expected to take decades, are being beaten regularly. Who is to say how much AI could advance in the next 20-30 years?

"We've beaten some hard problems more quickly than expected therefore we'll likely beat other hard problems more quickly than expected" is logical induction. It's equivalent to "I just flipped a coin and got heads. I'll probably get heads again on the next flip." Don't do that. :)

Do you really believe there's less than a 50% chance strong AI won't be invented in your lifetime?

I don't know. I don't really see the value in speculating.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#194

Post by Scarblac »

faizshah wrote: post #160
simonbw wrote: post #112

Earlier quoted context omitted.

A computer won the Arimaa challenge last year. https://en.wikipedia.org/wiki/Arimaa

I guess the only thing left is to design a game where you can change the rules of the game as a turn.

Calvinball.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#195

Post by nl »

ubernostrum wrote: post #109
lololomg wrote: post #72

Earlier quoted context omitted.

'True AI will always be defined as anything a computer can not yet do'

Sort-of repeating a comment I made last time AlphaGo came up: As far as I know there is nothing particularly novel about AlphaGo, in the sense that if we stuck an AI researcher from ten years ago in a time machine to today, the researcher would not be astonished by the brilliant new techniques and ideas behind AlphaGo; rather, the time-traveling researcher would probably categorize AlphaGo as the result of ten years'…

It's easy to say that, in the same way that people now wouldn't be surprised if we could factor large numbers in linear time if we had a functional quantum computer!!

10 years ago no one believed it was possible to train deep nets[1].

It wasn't until the current "revolution" that people learned how important parameter initialization was. Sure, it's not a new algorithm, but it made the problem tractable.

So far as algorithmic innovations go, there's always ReLU (2011) and leaky ReLU (2014). The one-weird-trick paper was pretty important too.

[1] Training deep multi-layered neural networks is known to be hard. The standard learning strategy— consisting of randomly initializing the weights of the network and applying gradient descent using backpropagation—is known empirically to find poor solutions for networks with 3 or more hidden layers. As this is a negative result, it has not been much reported in the machine learning literature. For that reason, artificial neural networks have been limited to one or two hidden layers

http://deeplearning.cs.cmu.edu/pdfs/1111/jmlr10_larochelle.p...

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#196

Post by eru »

DavidSJ wrote: post #135
Fede_V wrote: post #93

Earlier quoted context omitted.

That's incorrect. The features that AlphaGo uses are not pixel level features, but board states - and the architecture between AlphaGo and the Atari network is completely different. It's still an incredibly achievement - but it's important to be accurate.

For AlphaGo, a "pixel" is a point on the board. It uses essentially the same convolutional neural networks (CNNs) that are in state-of-the-art machine vision systems. But yes, the overall architecture is rather different from the Atari system, due to the integration of that CNN with Monte Carlo Tree Search.

Actually, putting a piece of software in front that infers board states from a video feed would be an easy problem.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#197

Post by eru »

nl wrote: post #195
ubernostrum wrote: post #109

Earlier quoted context omitted.

Sort-of repeating a comment I made last time AlphaGo came up: As far as I know there is nothing particularly novel about AlphaGo, in the sense that if we stuck an AI researcher from ten years ago in a time machine to today, the researcher would not be astonished by the brilliant new techniques and ideas behind AlphaGo; rather, the time-traveling researcher would probably categorize AlphaGo as the result of ten years'…

It's easy to say that, in the same way that people now wouldn't be surprised if we could factor large numbers in linear time if we had a functional quantum computer !! 10 years ago no one believed it was possible to train deep nets[1]. It wasn't until the current "revolution" that people learned how important parameter initialization was. Sure, it's not a new algorithm, but it made the problem tractable. So far as al…

Dropout (and maxout) might also count.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#198

Post by lmm »

ubernostrum wrote: post #109
lololomg wrote: post #72

Earlier quoted context omitted.

'True AI will always be defined as anything a computer can not yet do'

Sort-of repeating a comment I made last time AlphaGo came up: As far as I know there is nothing particularly novel about AlphaGo, in the sense that if we stuck an AI researcher from ten years ago in a time machine to today, the researcher would not be astonished by the brilliant new techniques and ideas behind AlphaGo; rather, the time-traveling researcher would probably categorize AlphaGo as the result of ten years'…

The effectiveness? Ten years ago researchers thought humanlike intelligence must necessarily involve something more than simple techniques. Today that position becomes a lot harder to defend.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#199

Post by nl »

panic wrote: post #81
brian_cloutier wrote: post #71

Earlier quoted context omitted.

Forest for the trees. Monte Carlo Tree Search was necessary and itself a massive improvement over minimax but not sufficient for creating a Go program to challenge professional players. The true innovation here is the neural networks. Without those networks to guide it AlphaGo plays far worse than existing programs. The fact that those networks are sufficient is pretty incredible. We already knew that by inventing th…

It's totally impressive! I'm excited for the future of DeepMind and to see what other kinds of things we can build from neural networks. I'm just saying that we have to be careful with what kind of intelligence we ascribe to an algorithm like this. An AI is not going to take over the world by impressing us with its game-playing skills.

DeepMind is the company/lab Google bought. The algorithm is more properly called AlphaGo.

Re: AlphaGo beats the world champion Lee Sedol in first of five matches

#200

Post by eru »

argonaut wrote: post #168
ogrisel wrote: post #136

Earlier quoted context omitted.

You can do math with continuous and infinite dimensional spaces.

And? This does not address my argument that the complexity is beyond-combinatorially explosive (infinite spaces). I'm not talking about the space of possible board states. I'm talking about merely the set of all possible actions. EDIT: clarified my language to address below reply.

Go is combinatorially explosive, too.
Post reply on HN