Boardgames like Go are devoid of nebulosity (http://meaningness.com/nebulosity ), which is the main source of difficulty in the real world.
-
-
Replying to @Meaningness
The deep-learning image recognition results are genuinely interesting—unlike the Go ones—because recognition is a real, and nebulous, task.
1 reply 0 retweets 3 likes -
Replying to @Meaningness
Boardgame programs all have two parts: tree search to look ahead at future moves, and a static evaluator that says how good the board looks
1 reply 0 retweets 1 like -
Replying to @Meaningness
Computers win at chess by brute force: searching possible moves much further ahead than humans, evaluating millions of possibilities.
1 reply 0 retweets 0 likes -
Replying to @Meaningness
It has always been known that brute-force tree search won’t work for Go; there are too many possible moves. So, you need a better evaluator.
1 reply 0 retweets 0 likes -
Replying to @Meaningness
The standard analysis of Go has always been that grandmasters see regional patterns on the board that are good or bad. That’s evaluation.
1 reply 0 retweets 1 like -
Replying to @Meaningness
What Google did was spend incredible quantities of computer time playing vast numbers of games—noting which board configurations led to wins
1 reply 0 retweets 1 like -
Replying to @Meaningness
It is hard to see how this strategy could have not-worked.
2 replies 0 retweets 0 likes -
Replying to @Meaningness
Only question is whether the AlphaGo “neural” network did any non-obvious generalization. I don’t have access to the journal article, but >
2 replies 0 retweets 0 likes -
Replying to @Meaningness
@Meaningness https://web.archive.org/web/20160128151110/https://storage.googleapis.com/deepmind-data/assets/papers/deepmind-mastering-go.pdf … but tbqh I wasn't too impressed with "look! you can mapreduce with hybrid [sup|unsup]ervised systems!"2 replies 0 retweets 1 like
-
-
Replying to @Meaningness
@Meaningness tell me when you're done and let's salvage something from our mutual disappointment0 replies 0 retweets 1 likeThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.