I think winning against this DCNN is quite easy. Play unusual shapes and start fights. Since it can't calculate it will probably fail.

Looks like you should just go play it then. Let me know when you do - I'd love to watch!

_________________
Todd K. Pedlar
Associate Professor of Physics, Luther College
Decorah, IA

I just noticed in one game that the network can't even read ladders. So an easy solution would be to start a ladder that works for you.

You are making some assumptions (mistake) about how a neural net, or a MCTS program for that matter, works.

MCTS -- in its purest form, very simple but too slow. And THAT is the "ladder problem", not that it doesn't read ladders, because the pure form isn't reading ANYTHING. It is an "evaluator", is move "a" better than move "b" based on the concept that if ENOUGH random games are played form that point on by two EQUAL players (equally good or equally bad) and a higher precentage of games is won following move "a" than following move "b" then "a" is better than "b". The "ladder problem" (and similar things)with this simple form is that "enough would be enormous. the "equally bad" players have rules to guide them, not random play << eg: recognize an "ladder" and get the laddering moves into the tree >>

So how MCTS performs is a tradeoff on these special rules controlling how moves get added to the tree to speed things up while hopefully not pruning away the right best move.

Neural nets are TRAINED. What they are is something that computes a function. Given an input, produce an output (position => next move or perhaps small set of moves to be fed to a MCTS evaluator). The large database of games is the TRAINING DATA. Think of this as a multi-dimentional array of cell values with connections between some cells. During training, cell values are altered and how values transfer through connection according to whether it gave a right answer (reward) or a wrong one (give those values and connection coefficients small random changes until helps with the answer for that position without hurting the results for the other positions; then on to the next training position. There's more to this. Ever so often, a random small disturbance to all values and connections, and retrain (that's called "annealing", necessary to get off false summits).

The point I am making is that the neural net doesn't contain that database of game records in their original form. What has been learned has been internalized in the final version of cell values and connection coefficients << note: training the neural net is time consuming (computationally intensive) but once you have a trained neural net you can "clone it" instead of having to train a copy (simply initialize to all those cell values and connection coefficients).

What is interesting about neural nets is the trainer doesn't have to know how to it (evaluate the function) but just be able to tell right answer from wrong (the assumption here is that the record of a game between high level experts represent almost all correct moves).

Understand? Sticking to ladders for example, doesn't have to "know" about ladders. In the position where a ladder COULD have been a factor, the expert didn't play in a certain way or perhaps played a move that was a ladder breaker preventing the ladder from materializing. The neural net doesn't "know" anything. Look, at THIS level (the level of the internals in your brain) you don't know anything either. Just signals going between a net of neurons.

BEFORE HAVING BEEN TRAINED (to some specific task) there is no difference between neural nets of the same complexity. In other words, the neural net program is "general purpose". Only the DATA stored during the training process would distinguish between one to play go, to play chess, or drive a car (I know Carnegie Mellon had a neural net doing that quite a ways back)

I looked at its games, and while there were a few fighting/reading sequences that seemed dodgy to me, there were not many. I'm at least 4 stones weaker, so I'm sure a dan player would see more holes, but I don't know if the bot has any obvious weaknesses a kyu player can exploit.

_________________
Occupy Babel!

Misunderstanding the generality of a DCNN. They are evaluating a function and the function could be anything. Useful for when those training them DON'T know how to do it, just can tell right result from wrong.

Image recognition a good example. Say it's face recognition. The trainers know for each face what the correct name is and in this case they can themselves learn to perform this task (assigning name to face) BUT they don't really know how they do that. Nor is it necessary that the be able to do it. All they need is a good supply of images for each face to be recognized, each correctly labeled. A DCNN can then be trained to recognize the faces that but NOT because "good at recognizing shapes/patterns". You have just read in a "how accomplished" but that doesn't make sense when a neural net is involved. They "just work" (once the cell values and inter-cell connection coefficients have been properly adjusted, and that adjustment is by random trial and error. Under training the originally blank neural net evolves to one that correctly evaluates the desired function.)

Think of biological evolution. No PLAN involved << sorry if I just offended "intelligent design" folks; but the real thing is more elegant and robust than "by design" >>

Off topic:

Interesting consequences of having an AI stronger that humans : intrinsic time-independant ratings.

http://www.cse.buffalo.edu/~regan/paper ... eHa11c.pdf

_________________
La victoire est un hasard, la défaite une nécessité.

I will now retract my claim. The DCNN is quite strong (I still didn't play it)

I was able to win against 5/6 dans on KGS and plays on a stable 3d - 4d

However there is another theory that I have, the bot actually plays bad because it plays amateurs and not pros. Remember that it was trained on pro games.

It would be interesting to see it play against a pro but without pro knowing it is a bot (thus preventing the pro from playing overplays thinking the computer will fail to win the fight)

The NN plays quite good in the opening but it is the middle game that the most mistakes are made.

I have watched it play almost pro like only to blunder groups for no reason.

Mark Zuckerberg (Facebook boss) just made a post about their Go Ai with a link to that paper, I wonder if that'll get more people interested in and playing Go?

The link, Uberdude, THE LINK!!!!1

https://www.facebook.com/zuck/videos/10102619979032811/

_________________
“The only difference between me and a madman is that I’m not mad.” — Salvador Dali ★ Play a slooooow correspondence game with me on OGS?

How did you find that link? I find it increasingly hard to get urls out of facebook, part of their siloization of the internet.

This certainly ought to generate some publicity, let's hope it brings a few new players into the game, even if the machines are getting closer to beating us all.
If only Zuckerb0rg would set the AI team to work on a manga.

_________________
North Lecale

This is the end of humanity. Matrix/Skynet is coming

BBC article based on it:

http://www.bbc.co.uk/news/technology-35419141

They're competing in the monthly KGS bot tournaments, and doing pretty well. http://www.weddslist.com/kgs/past/119/index.html

_________________
Occupy Babel!

Seems there is an easy way to make it stronger here. And how is it possible for a bot not to make a move on time?

Hoho, ironic when Zuckerberg says


Also the bragging about only taking 6 months seems a bit off to me, but I suppose you don't get to be a billionaire by being modest. Did the Facebook researchers really work in isolation of all previous Go AI research and invent everything themselves, or are they building on the work of others (both in neural net and Mogo-style MCTS techniques)?

more important than the link to the video is the link to the paper
http://arxiv.org/abs/1511.06410
http://arxiv.org/pdf/1511.06410v2.pdf

Well, that paper link was already posted by yoyoma, so for me it was more interesting that Zuckerberg made a public post about Go as that will have millions of readers, so could do a lot to spread word of the game and generate interest. Would be good if there was a highly rated comment below along the lines of "Want to learn how to play this game, check out the American Go Association at www.usgo.org or play online at www.gokgs.com"