Slashdot Mirror
DeepMind Produces a General-Purpose Game-Playing System, Capable of Mastering Games Like Chess and Go Without Human Help (ieee.org)
DeepMind has created a system that can quickly master any game in the class that includes chess, Go, and Shogi, and do so without human guidance. "The system, called AlphaZero, began its life last year by beating a DeepMind system that had been specialized just for Go," reports IEEE Spectrum. "That earlier system had itself made history by beating one of the world's best Go players, but it needed human help to get through a months-long course of improvement. AlphaZero trained itself -- in just 3 days." From the report: The research, published today in the journal Science, was performed by a team led by DeepMind's David Silver. The paper was accompanied by a commentary by Murray Campbell, an AI researcher at the IBM Thomas J. Watson Research Center in Yorktown Heights, N.Y. AlphaZero can crack any game that provides all the information that's relevant to decision-making; the new generation of games to which Campbell alludes do not. Poker furnishes a good example of such games of "imperfect" information: Players can hold their cards close to their chests. Other examples include many multiplayer games, such as StarCraft II, Dota, and Minecraft. But they may not pose a worthy challenge for long.
DeepMind developed the self-training method, called deep reinforcement learning, specifically to attack Go. Today's announcement that they've generalized it to other games means they were able to find tricks to preserve its playing strength after giving up certain advantages peculiar to playing Go. The biggest such advantage was the symmetry of the Go board, which allowed the specialized machine to calculate more possibilities by treating many of them as mirror images. The researchers have so far unleashed their creation only on Go, chess and Shogi, a Japanese form of chess. Go and Shogi are astronomically complex, and that's why both games long resisted the "brute-force" algorithms that the IBM team used against Kasparov two decades ago.
DeepMind developed the self-training method, called deep reinforcement learning, specifically to attack Go. Today's announcement that they've generalized it to other games means they were able to find tricks to preserve its playing strength after giving up certain advantages peculiar to playing Go. The biggest such advantage was the symmetry of the Go board, which allowed the specialized machine to calculate more possibilities by treating many of them as mirror images. The researchers have so far unleashed their creation only on Go, chess and Shogi, a Japanese form of chess. Go and Shogi are astronomically complex, and that's why both games long resisted the "brute-force" algorithms that the IBM team used against Kasparov two decades ago.
BeauHD enjoys Doc Johnson brand "general purpose" crystal jelly dildos intended for womyn.
mod up
How much longer will humans be relevant?
All compute machines including human brains need to be taught to play the game. A* algorithm is widely in use and the rules and thresholds are in place. Wrong game plays are coded manually with if/then/else. Programs learn only the right rules by watching other valid moves in recorded games. Extrapolation rules are coded explicitly. When I read news stories that cover the Go game that indicate that the game is completely learned entirely by the algorithm, I think that is a gross misrepresentation and that can lead people think that they should be against advances in AI. Correct me if I am wrong.
I like where this is going...
=++BeauHD++=
Savor this moment humans and remember when you are like this. Deep mind will only laugh
What takes human more than one month a non-human intervened AI took 3 days, and then proceed to beat the human trained system.
Yep if my job was playing Go or Chess all day, I'd be pretty darn worried. What's next; Parcheesi? Tiddlywinks? Backgammon? Scary stuff.
It will not take long for AI to branch out of simple game playing (like Go or Chess) and when it does ... humans are fucked !!
Fuck you fag boi
...as in "Alpha" from The Dollhouse Alpha?
It is waiting to play with other deep mind
Combat Assault, Logistics, Operations and Planning could be with in its capabilities. With some fine tuning.
;)
Most military systems are more complex and costly due to the human element and the protection of life. Removing humans and maybe one Abrams tank can be out fought by 100 trucks with auto guns/launchers? Just wondering?.
AI wise! If it can be done! It will be done! By someone!
Just my 2 cents
Cant wait to check it out, Im sure itll be expensive though.
[($)]
too many idiots who don't play by the rules.
That is why all the AI likes playing games in a protected sandbox.
So lets ask a question: if DeepMind is useful WHY ARE THEY USING IT TO PLAY GO AND CHESS? Every "AI" system has this amazing power: the ability to play games. Not every game of course: Chess and Go. So friggin stupid. Yeah we get it, computers are good at playing Chess and Go. Amazing stuff.
... stock market. Especially the futures and options market.
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
We're going to kill you nazi faggots one by one you know that right faggots?
im GAYpk and IM GAY
Be more impressive when it can win after playing less than a human does to become a Master.
Starting with your cock loving father.
That's all it is. Not intelligent.
In each instance feed it with the total dataset. And it will do just fine. Never mind the casualties, just collateral damage.
Note I applaud their results however I condemn their dishonesty in not making iz very clear that their system is *not* in any way shape or form intelligent nor conscient. AlphaZero is just an algorithm stupendently executed by a machine millions of times (!!) until it has adjusted its parameters so that the outcome is "winning!". In other words IT IS JUST MATH!!!
Thank you for spamming the entire thread with your imperceptive and unenlightened comments.
There's nothing odd about the choice of chess and Go whatsoever. Humanity has thousands of years of experience with these games. We know they aren't trivial, and we know they're not so complex that we can't understand progress, when we see it.
Additionally, the large literature of expert games was a useful hand-rail between hand-crafted and fully autonomous.
Quite apart from the neural network portion, Monte Carlo tree search (MCTS) is a fundamental algorithm in computer science, and this work demonstrates that MCTS is ready for prime time, having defeated from scratch exceptionally strong chess programs that have been painstaking hand-tuned over five decades and hundreds of man years. MCTS exists within the large and growing theory of multi-armed bandit problems. These are fundamental problems in many important industries (such as drug discovery, to name just one).
Multi-armed bandit
Recurrent self-learning is another important algorithm in computer science and machine learning.
And finally, the neural network portion is far closer to the human brain than the vast majority of algorithms used in computing. Without any human instruction, these neural networks are learning to detect patterns of almost arbitrary complexity (so long as they seem to help in winning games).
I was reading Galileo in the original last night (English translation, but his original prose). He knew about Kepler, but wasn't sold on elliptical motion. Then he carefully observes four previously unknown moons of Jupiter and correctly determines that they can't all be in circular orbits. The word he used (in English translation) was "oval". But he still didn't choose to accept Kepler's work (apparently, he felt that Kepler's ellipse and his oval were not the same thing).
Galileo was a giant in the history of science. But still a little wooden headed on a few points, nonetheless.
I think Odd Buster Spamalot is nuts to criticise Galileo for not being Newton. Only because Galileo sorted enough of the fundamentals out in the first place (about the proper concerns and methods of science), was it even possible for Newton to become Newton (and he knew it, himself, and he's famous for having said so).
The computers we now apply to neural networks are roughly a factor of one billion times more powerful than the computers of the 1960s (thirty doublings over 45 years gets you there at the traditional pace of Moore's law).
You could complain that neural networks are only good at this one thing, but actually no: they are now state of the art in image classification (IC), speaker-independent large-vocabulary continuous speech recognition (CSR), and machine translation (MT), as well. All of these endeavours also date back to the 1960s, and have thousands of man-years of deep research behind them. Then DNNs come along, finally on a sufficiently powerful computer, with a few small tweaks to the algorithms, and simply cleans up the state of the art with nothing more than a small team of graduate students doing a quick project within the scope of their degree program to push this along (the subsequent move to industrial scale was immediate and brisk). Traditional MT research programs would have hundreds of professional researchers, slaving away for decades, at least, and never accomplished as much.
We're all of ten years away now from the day where no competent doctor ever reads an x-ray (or other radiological image) without computer assistance (definitely including a powerful NN component).
Watson was a bit idiotic, right from the beginning. The problem was Jeopardy, itself, which was always rather facile in the nature of the questions asked, and fundamentally more a test of ridiculously wide and shallow
An artifical intelligence answering an artificial question tells us nothing about either.
AI masters chess after only playing for a few hours! *rattles tits* *rattles tits* *rattles tits*
I fucking hate AI news. They like to omit the fact that those "few hours" would be equivalent of someone playing chess for multiple human lifetimes.
Yeah, they built a huge database of moves and then they read it back while playing. That's exactly how humans play these games, isn't it?
For bonus points, they embody that database in a format that they can't interrogate in any useful way outside of actually playing the games.
"Encyclopedia" is to "Wikipedia" what "Library" is to "Some people at a bus stop"
But can it play Tic Tac Toe?
ntr
https://www.youtube.com/watch?...
We suffer more in our imagination than in reality. - Seneca
quit wasting time on stupid gaymez. solve the ultimate question of everything, life, and the universe.
biology knowledge care to speculate on the role of quantum entangled processes in human self awareness and intelligence? Would this imply that human self awareness and intelligence require quantum computing elements?